AI 900 Exam Free Actual Q As Page 1 ExamTopics PDF

6/17/2021 AI-900 Exam – Free Actual Q&As, Page 1 | ExamTopics
- Expert Verified, Online, Free.
 Custom View Settings
Topic 1 - Single Topic
https://www.examtopics.com/exams/microsoft/ai-900/custom-view/ 1/132
Question #1 Topic 1
A company employs a team of customer service agents to provide telephone and email support to customers.
The company develops a webchat bot to provide automated answers to common customer queries.
Which business benefit should the company expect as a result of creating the webchat bot solution?
A. increased sales
B. a reduced workload for the customer service agents
C. improved product reliability
Correct Answer: B
  abhi0706 Highly Voted  8 months, 1 week ago

B is correct
upvoted 14 times
  ksarhan Highly Voted  8 months ago

B is correct
upvoted 7 times
  berserkguts Most Recent  2 weeks, 1 day ago

this was in my exam yesterday, May 31
upvoted 1 times
  SQLNh 1 month ago

B is correct
upvoted 1 times
  freshmaker 1 month, 1 week ago

got this q
upvoted 1 times
  sandykond 1 month, 1 week ago

B is the correct answer
upvoted 1 times
  LPatel 1 month, 2 weeks ago

Vote for B
upvoted 1 times
  saksam89 1 month, 2 weeks ago

C is correct
upvoted 1 times
  techifiedMercy 1 month, 3 weeks ago

B is correct
upvoted 1 times
  Ash111 2 months, 1 week ago

B is the correct
upvoted 1 times
  Samiat 2 months, 2 weeks ago

B is correct.
upvoted 1 times
  vickkywyze 2 months, 2 weeks ago

option is best answer
upvoted 1 times
  cron0001 2 months, 2 weeks ago

B is correct for me
upvoted 1 times
  hibana2077 2 months, 2 weeks ago

B is correct
upvoted 1 times
  ShefAZ 2 months, 3 weeks ago

In exam 27 March
upvoted 1 times
  Floxzy 2 months, 3 weeks ago

I will go with B
upvoted 1 times
  agsite 2 months, 3 weeks ago

For me B is correct.
upvoted 1 times
Question #2 Topic 1
For a machine learning progress, how should you split data for training and evaluation?
A. Use features for training and labels for evaluation.
B. Randomly split the data into rows for training and rows for evaluation.
C. Use labels for training and features for evaluation.
D. Randomly split the data into columns for training and columns for evaluation.
Correct Answer: Answer: B

In Azure Machine Learning, the percentage split is the available technique to split the data. In this technique, random data of a given percentage
will be split to train and test data.
Reference:
https://www.sqlshack.com/prediction-in-azure-machine-learning/
  ExamPwnr Highly Voted  8 months, 2 weeks ago

You split rows not columns:
https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/split-data#how-to-configure-split-data
upvoted 56 times
  amvi Highly Voted  8 months, 2 weeks ago

Answer should be B.
https://docs.microsoft.com/en-us/azure/machine-learning/algorithm-module-reference/split-data
upvoted 13 times

upvoted 1 times
  AshishScotia 2 weeks, 3 days ago

Please change the correct answer to B
upvoted 1 times
  Ajao 1 month ago

Random splitting data into rows for training and evaluation is best which will have all column topics as appropriate
upvoted 1 times

Answer should be B.
upvoted 1 times

got this q
upvoted 1 times
  Rishubelgium 1 month, 1 week ago

Answer should be B
upvoted 1 times
  kheiro 1 month, 1 week ago

Answer is B
upvoted 1 times
  Kanjati 1 month, 1 week ago

Answer is B
upvoted 1 times
  Ebenezer 1 month, 2 weeks ago

You randomly split the data into rows for training and column for evaluation. i
upvoted 1 times

Rows should be split not columns
upvoted 1 times
  CherryCarpo 2 months ago

Answer should be B
upvoted 2 times
  Ifexalex 2 months, 1 week ago

upvoted 2 times
  vickkywyze 2 months, 2 weeks ago

b is selected as answer
upvoted 2 times

Should be B, rows not columns
upvoted 2 times

In exam 27 March
upvoted 2 times
Question #3 Topic 1
HOTSPOT -
You are developing a model to predict events by using classification.
You have a confusion matrix for the model scored on test data as shown in the following exhibit.
Use the drop-down menus to select the answer choice that completes each statement based on the information presented in the graphic.
NOTE: Each correct selection is worth one point.
Hot Area:
Correct Answer:
Box 1: 11 -
TP = True Positive.
The class labels in the training set can take on only two possible values, which we usually refer to as positive or negative. The positive and
negative instances that a classifier predicts correctly are called true positives (TP) and true negatives (TN), respectively. Similarly, the
incorrectly classified instances are called false positives (FP) and false negatives (FN).
Box 2: 1,033 -
FN = False Negative -
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/studio/evaluate-model-performance
  Vijaya Highly Voted  8 months, 2 weeks ago

Answer 2 is also correct please refer the https://docs.microsoft.com/en-us/azure/machine-learning/classic/evaluate-model-performance
upvoted 16 times
  denizej Highly Voted  7 months, 3 weeks ago

Answer 2 is correct. The grid used in the question is reversed to the MS documentation. A false negative would imply that a 0 was predicted but 1
was the actual outcome, of which there were 1033 occurrences according to the grid used in the question.
upvoted 7 times
  SnowCheetah Most Recent  1 week, 4 days ago

predicted positive should be mean by True positive. if that the case, answer was correct based on document https://docs.microsoft.com/en-
us/azure/machine-learning/classic/evaluate-model-performance
upvoted 1 times
  berserkguts 2 weeks, 1 day ago

upvoted 1 times

The answer is correct, but the confusion matrix box is incorrect for False Positive and False Negative
upvoted 1 times
  Kanjati 1 month ago

True positive is 11 and false negative is 1033
upvoted 2 times

https://miro.medium.com/max/2102/1*fxiTNIgOyvAombPJx5KGeA.png here is a diagram you must know
upvoted 2 times

got this q
upvoted 1 times
  afzal95 2 months, 1 week ago

isnt 13951 the answer for false negative?
upvoted 1 times

Given answer is correct. As predicted positive is true positive and false negative = predicted negative but true positive
upvoted 1 times
  pooja11284 2 months, 2 weeks ago

given answer is correct
upvoted 2 times

In exam 27 March
upvoted 1 times
  Nandy_Shree 2 months, 3 weeks ago

Given answer is correct only. See predicted and actual as ulta values.
upvoted 1 times
  CollinsMarcus 2 months, 3 weeks ago

Answer 2 is correct
upvoted 1 times
  Arocmd9 2 months, 4 weeks ago

11 and 1033
upvoted 1 times
  lvbranco 3 months, 3 weeks ago

Answer 2 is super correct. Just inversed the matrix, but correct.
upvoted 3 times
  ramjisriram 4 months, 1 week ago

Given answers are correct. Verified.
upvoted 1 times
Question #4 Topic 1
You build a machine learning model by using the automated machine learning user interface (UI).
You need to ensure that the model meets the Microsoft transparency principle for responsible AI.
What should you do?
A. Set Validation type to Auto.
B. Enable Explain best model.
C. Set Primary metric to accuracy.
D. Set Max concurrent iterations to 0.
Correct Answer: B
Model Explain Ability.
Most businesses run on trust and being able to open the ML ‫ג‬€black box‫ג‬€ helps build transparency and trust. In heavily regulated industries
like healthcare and banking, it is critical to comply with regulations and best practices. One key aspect of this is understanding the relationship
between input variables (features) and model output. Knowing both the magnitude and direction of the impact each feature (feature
importance) has on the predicted value helps better understand and explain the model. With model explain ability, we enable you to understand
feature importance as part of automated ML runs.
Reference:
https://azure.microsoft.com/en-us/blog/new-automated-machine-learning-capabilities-in-azure-machine-learning-service/
  ipindado2020 Highly Voted  6 months, 2 weeks ago

b is ok
upvoted 7 times
  mnmcbl Most Recent  2 days, 22 hours ago

B for sure
upvoted 1 times
  cbeqs 1 month, 1 week ago

Yes I go with B only
upvoted 2 times

B is the correct answer.
upvoted 1 times
  saksham_123 2 months ago

ok is b
upvoted 1 times
  bo55 6 months, 1 week ago

B is true
upvoted 2 times
Question #5 Topic 1
HOTSPOT -
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
Hot Area:
Correct Answer:
Anomaly detection encompasses many important tasks in machine learning:

Identifying transactions that are potentially fraudulent.
Learning patterns that indicate that a network intrusion has occurred.
Finding abnormal clusters of patients.
Checking values entered into a system.
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/anomaly-detection
  sudheesh Highly Voted  8 months, 2 weeks ago

N/Y/N ?
upvoted 73 times
  n1a2m3e3 5 months, 2 weeks ago

N/Y/N is correct
upvoted 6 times
  brianp 8 months, 1 week ago

Agreed - N/Y/N (regression, anomaly, classification)
upvoted 21 times
  PremT Highly Voted  8 months, 1 week ago

even i feel answer shld be N-Y-N
upvoted 13 times
  SR2905 Most Recent  3 days, 11 hours ago

No
Yes
No
upvoted 1 times
  anasmmg 1 month ago

I found the video useful in this article
https://www.anodot.com/blog/what-is-anomaly-
detection/#:~:text=Anomaly%20detection%20(aka%20outlier%20analysis,a%20change%20in%20consumer%20behavior.
which already helps me to decide that C has to be YES because it talks about two things:
First it says: " a patient WILL develop " which means it's not like classification examples we have from microsoft before "Does he has Diabeties or
not?".
Second point is " patient's medical HISTORY" which completely shows that it might be regression or Anomaly detection, but I prefered Anomaly
detection to regression because regression should refers to an integer results, while Anomaly detection will referes to abnoraml increasing of sugar
in blood which will allows DRs to warning the patient in advance
upvoted 4 times
  allanm 1 month, 1 week ago

ANSWER: N/Y/N
C is No because predicting a patient developing diabetes or not is a CLASSIFICATION problem. This is infact the introduction example given by MS
in their learning pathway for creating a Classification model -
https://docs.microsoft.com/en-gb/learn/modules/create-classification-model-azure-machine-learning-designer/introduction
upvoted 1 times
  Rishubelgium 1 month, 1 week ago

N/Y/N is correct answer
upvoted 3 times
  Chinnathala 1 month, 2 weeks ago

Answer is No / Yes / Yes. Googled this and found this article, this is not related to exam but can be used as reference
https://www.sciencedirect.com/science/article/pii/S2405959518304624
My previous comment was typo.

upvoted 1 times
  Chinnathala 1 month, 2 weeks ago

Answer is No / Yes / No. Googled this and found this article, this is not related to exam but can be used as reference
https://www.sciencedirect.com/science/article/pii/S2405959518304624
upvoted 1 times
  londonboy 1 month, 2 weeks ago

answer should be N-Y-N
upvoted 1 times

No Yes No
upvoted 1 times
  Praveen_AI_ML 2 months ago

If there is anomaly in the health report over the time, it could not be just diabetes, it could be anything like thyroid, BP, covid etc etc.... Here it is
asking to predict specifically diabetes, it must be a classification problem. N/Y/N should be correct.
upvoted 1 times
  SnakePlissken 2 months ago

Third case: No (with some doubt)
At first, I thought it was easy because it looked like an Microsoft Learn example, but there is a difference.
MS example: "A health clinic might use the CHARACTERISTICS of a patient (such as age, weight, blood pressure, and so on) to predict whether the
patient is at risk of diabetes."
This case: "Predicting whether a patient will develop diabetes based on the patient's MEDICAL HISTORY..."
In the MS example you have data from one moment, in this case you have ongoing changing data in time. I think they use some recent data for the
prediction, and not a change in data, but I'm still not 100% sure...
https://docs.microsoft.com/en-us/learn/modules/create-classification-model-azure-machine-learning-designer/introduction
upvoted 2 times

NO/YES/NO
upvoted 1 times

N/Y/N for me too.
upvoted 1 times
  Adedoyin_Simeon 2 months, 2 weeks ago

The correct answer is
No, Yes, No
Third case is a classification problem not an anomaly detection
upvoted 1 times
  Jolin130 2 months, 3 weeks ago

I think the key points are 'develop' and 'based on the same patient's medical history', which is similar to the second case where the user has a
normal pattern of logins, but then anomaly is detected once the login has a deviated pattern.
In the third case, the medical history of that patient can be deemed as the normal pattern, and anomaly would be detected once the the patient, as
time goes by, develops deviated and unusual pattern. So I would go with N/Y/Y.
upvoted 3 times
  msp1 2 months, 2 weeks ago

Excellent way to explain! I agree with N/Y/Y
upvoted 1 times
  Amoslee 2 months, 3 weeks ago

So what's the correct answer?
upvoted 1 times
Question #6 Topic 1
HOTSPOT -
To complete the sentence, select the appropriate option in the answer area.
Hot Area:
Correct Answer:
Reliability and safety:

AI systems need to be reliable and safe in order to be trusted. It is important for a system to perform as it was originally designed and for it to
respond safely to new situations. Its inherent resilience should resist intended or unintended manipulation. Rigorous testing and validation
should be established for operating conditions to ensure that the system responds safely to edge cases, and A/B testing and
champion/challenger methods should be integrated into the evaluation process.
An AI system's performance can degrade over time, so a robust monitoring and model tracking process needs to be established to reactively
and proactively measure the model's performance and retrain it, as necessary, to modernize it.
Reference:
https://docs.microsoft.com/en-us/azure/cloud-adoption-framework/innovate/best-practices/trusted-ai
  Pukk Highly Voted  8 months, 1 week ago

I think “Reliability and safety” is correct option as per the following:
“To build trust, it's critical that AI systems operate reliably, safely, and consistently under normal circumstances and in unexpected conditions. These
systems should be able to operate as they were originally designed, respond safely to unanticipated conditions, and resist harmful manipulation.
It's also important to be able to verify that these systems are behaving as intended under actual operating conditions. How they behave and the
variety of conditions they can handle reliably and safely largely reflects the range of situations and circumstances that developers anticipate during
design and testing.
We believe that rigorous testing is essential during system development and deployment to ensure AI systems can respond safely in unanticipated
situations and edge cases, don't have unexpected performance failures, and don't evolve in ways that are inconsistent with original expectations”
upvoted 59 times
  KASTURI Highly Voted  8 months ago

Yes "Reliability and Safety" is the correct answer. I found this question correctly marked in another question bank.I passed my exam last week with
930 marks.
https://www.udemy.com/course/microsoft-certified-azure-ai-fundamentals-5-practice-tests/?referralCode=611411548EFB2239FD69
upvoted 18 times
  elibrahimov396 2 months, 3 weeks ago

Hi.Can you share this is course for me?
upvoted 1 times
  NKT 6 months, 3 weeks ago

Thanks for this reference of another question bank.
upvoted 3 times

upvoted 1 times

Reliability and Safety is the correct answer.
upvoted 1 times
  deveast 1 month, 1 week ago

Reliability and safety
upvoted 2 times

upvoted 2 times

Reliability and safety seems correct
upvoted 1 times

Reliability and safety. It's straight to the point. English
upvoted 1 times
  gills 2 months ago

I think everyone here is thinking of missing values should be "fixed" and unusual values be fixed as well. So you are coming from data
transformation so data is accurate and the model will be a lot more accurate in predicting. That is not the point for this question.
This question is about not letting people who use the model predict personal information or private information which was used to train the model
in the first place. So putting in missing values or odd values does skew the model prediction and yet at the same time it protect the privacy of the
data used to train the model in the first place.
So answer is privacy and safety.

upvoted 1 times

Not about privacy! How reliable is the model if it has missing values!
upvoted 1 times
  Abdulwasiu 2 months, 2 weeks ago

Reliability and Safety... missing values in training data might result in the model acting or producing strange result, which makes it unreliable and
unsafe in critical applications like aircraft systems.
upvoted 2 times

I reckon answer is Reliability and Safety
upvoted 1 times
  ESEI 2 months, 3 weeks ago

"Reliability & Safety". This question reminds me of Tay; https://en.wikipedia.org/wiki/Tay_(bot)
upvoted 1 times
  RajeshDB 3 months ago

Answer is Reliability & Safety
upvoted 1 times
  Bhadu 3 months ago

upvoted 1 times
  Graz21 3 months ago

I would say “Reliability and safety”.
If you read MS documentation about responsible AI, under “Reliability and safety” it says "Its inherent resilience should resist intended or
unintended manipulation". Unusual data values may come from data manipulation to influence the AI in some way, so I'd stick with "Reliability and
safety".
upvoted 1 times
  Massy 3 months, 1 week ago

Why Reliability and safety? I thinlk it's Transparency
upvoted 2 times
  dennis 3 months, 3 weeks ago

Answer should be Reliability and Safety
upvoted 1 times
Question #7 Topic 1
DRAG DROP -
Match the types of AI workloads to the appropriate scenarios.
To answer, drag the appropriate workload type from the column on the left to its scenario on the right. Each workload type may be used once,
more than once, or not at all.
Select and Place:
Correct Answer:
Box 3: Natural language processing

Natural language processing (NLP) is used for tasks such as sentiment analysis, topic detection, language detection, key phrase extraction, and
document categorization.
Reference:
https://docs.microsoft.com/en-us/azure/architecture/data-guide/technology-choices/natural-language-processing
  gargaditya Highly Voted  7 months, 2 weeks ago

Answer is correct.
What is Natural Language Processing?

Natural language processing (NLP) is the area of AI that deals with creating software that understands written and spoken language.
NLP enables you to create software that can:
-Analyze text documents to extract key phrases and recognize entities (such as places, dates, or people). ie Text Analystics service
-Perform sentiment analysis to determine how positive or negative the language used in a document is. ie Text Analytics service
-Interpret spoken language, and synthesize speech responses. ie Speech service(speech to text and text to speech)
-Automatically translate spoken or written phrases between languages. ie Text service(for text to text translation)/Speech service(for speech to
text/speech translation)
Interpret commands and determine appropriate actions. ie Language Understanding(LUIS) service

upvoted 26 times

upvoted 1 times

correct answer
upvoted 1 times

The answer is correct!
upvoted 1 times

upvoted 1 times

ANSWER IS CORRECT
upvoted 2 times
  heyshomy 2 months, 2 weeks ago

Conversational AI; Computer Vision and NLP to Answer Areas 1,2 and 3
upvoted 1 times

Answer is correct.
upvoted 1 times

In exam 27 March
upvoted 1 times
  Azurite 3 months, 2 weeks ago

Came in exam Feb 28
upvoted 2 times

Given answers are correct.
upvoted 2 times
  mirzamaan 7 months, 3 weeks ago

I think Last Question Correction is $th Option rather Last one coz NLP use for Natural Language Translation from one Language to other Langue's
and in last question its about data
upvoted 1 times
  Boney35 7 months, 2 weeks ago

Natural language processing (NLP) is used for tasks such as sentiment analysis.
upvoted 4 times
Question #8 Topic 1
You are designing an AI system that empowers everyone, including people who have hearing, visual, and other impairments.
This is an example of which Microsoft guiding principle for responsible AI?
A. fairness
B. inclusiveness
C. reliability and safety
D. accountability
Correct Answer: B
Inclusiveness: At Microsoft, we firmly believe everyone should benefit from intelligent technology, meaning it must incorporate and address a
broad range of human needs and experiences. For the 1 billion people with disabilities around the world, AI technologies can be a game-
changer.
Reference:
https://docs.microsoft.com/en-us/learn/modules/responsible-ai-principles/4-guiding-principles

b is ok
upvoted 14 times

upvoted 2 times

B is the answer
upvoted 2 times
  GodfreyMbizo 1 month ago

upvoted 2 times

got this q
upvoted 1 times
  steve202105 2 months, 1 week ago

B is the right answer
upvoted 1 times

Inclusiveness is True
upvoted 1 times

B should be right
upvoted 2 times

In exam 27 March
upvoted 1 times

b is right!
upvoted 1 times
  D_nice 3 months, 1 week ago

B is correct
upvoted 2 times

Came in exam Feb 28
upvoted 1 times
  Decent 3 months, 3 weeks ago
Inclusiveness "we firmly believe everyone should benefit from intelligent technology, meaning it must incorporate and address a broad range of
human needs and experiences. For the 1 billion people with disabilities around the world, AI technologies can be a game-changer."
upvoted 3 times
  adesal 3 months, 3 weeks ago

upvoted 2 times
Question #9 Topic 1
DRAG DROP -
Match the Microsoft guiding principles for responsible AI to the appropriate descriptions.
To answer, drag the appropriate principle from the column on the left to its description on the right. Each principle may be used once, more than
once, or not at all.
Select and Place:
Correct Answer:
Box 1: Reliability and safety -

To build trust, it's critical that AI systems operate reliably, safely, and consistently under normal circumstances and in unexpected conditions.
These systems should be able to operate as they were originally designed, respond safely to unanticipated conditions, and resist harmful
manipulation.
Box 2: Accountability -
The people who design and deploy AI systems must be accountable for how their systems operate. Organizations should draw upon industry
standards to develop accountability norms. These norms can ensure that AI systems are not the final authority on any decision that impacts
people's lives and that humans maintain meaningful control over otherwise highly autonomous AI systems.
Box 3: Privacy and security -

As AI becomes more prevalent, protecting privacy and securing important personal and business information is becoming more critical and
complex. With AI, privacy and data security issues require especially close attention because access to data is essential for AI systems to make
accurate and informed predictions and decisions about people. AI systems must comply with privacy laws that require transparency about the
collection, use, and storage of data and mandate that consumers have appropriate controls to choose how their data is used
Reference:
  Pukk Highly Voted  8 months, 1 week ago

For the 2nd question, shouldn’t it be “accountability” instead of “fairness”?
upvoted 46 times

Yes.
* Accountability *
upvoted 4 times
  vmontalvao 2 months, 3 weeks ago

That's also my opinion.
upvoted 3 times
  imcee_ Highly Voted  8 months ago

Accountability
upvoted 28 times

Yes, for the 2nd one.
upvoted 1 times

For the 2nd question, Accountability is the right answer.
Human is the ultimate owner of the AI system thus owns the control over the AI.
upvoted 1 times

upvoted 1 times

The answer for the 2nd is Accountability.
upvoted 1 times

Yey this is Accountability!
upvoted 1 times
  Alasco 2 months ago

"...to ensure that decisions made by AI systems can be overriden by humans"
Decisions made by AI can be bias at times thats why its important to allow humans to override some of these decisions to mitigate bias which is a
feature of Fairness. second answer is correct.
upvoted 2 times
  jd2 1 month, 1 week ago

I agree, to mitigate the possibility of bias
upvoted 1 times

Reliability and Safety/Accountability/Privacy and Security is my answer
upvoted 4 times

The second is "Reliability and safety" like the first
upvoted 6 times
  ChandrashekharDeshpande 3 months, 2 weeks ago

My suggestion is Reliability and Safety: Human judgment will be key to identifying potential blind spots and biases in AI systems.
upvoted 4 times

I think the answer is correct as it is
upvoted 2 times
  Ashwinee 4 months ago

I think 2nd question should be accountability :-Accountability
upvoted 5 times
  Naverick 5 months, 1 week ago

I believe the answer for the second scenario is also "Reliability and Safety", remember the question allows for a principal to be used more than
ones.
The scenario is able the ability to Override AI Decisions, this is clearly talking about the reliability and safety of the system.
"....Ultimately, because AI should augment and amplify human capabilities, people need to play a critical role in making decisions about how and
when an AI system is deployed, and whether it's appropriate to continue to use it over time. Human judgment will be key to identifying potential
blind spots and biases in AI systems."
upvoted 3 times
  nohaph 5 months, 2 weeks ago

the second should be accountability, not Fairness:

These norms can ensure that AI systems are not the final authority on any decision that impacts people's lives and that humans maintain
meaningful control over otherwise highly autonomous AI systems.
upvoted 4 times
  teamaws 6 months, 1 week ago

2nd is Accountability
Accountability
upvoted 3 times
  sreekarv 6 months, 1 week ago

2nd --> Accountability
upvoted 4 times
  ExamTopics007 6 months, 2 weeks ago

2nd --> Accountability
upvoted 6 times
Question #10 Topic 1
HOTSPOT -
Hot Area:
Correct Answer:
Reliability and safety: To build trust, it's critical that AI systems operate reliably, safely, and consistently under normal circumstances and in
unexpected conditions.
These systems should be able to operate as they were originally designed, respond safely to unanticipated conditions, and resist harmful
manipulation.
Reference:
  SQLNh Highly Voted  1 month ago

The answer is correct.
upvoted 5 times
  GodfreyMbizo Most Recent  1 month ago

emphasis is on Reliability and safety hence answer is correct
upvoted 3 times

upvoted 2 times
  Jeffdu 3 months ago

The key here is system resilience during unexpected events, so "reliability and safety" is the correct principle
upvoted 3 times
  olowoyinka 3 months, 2 weeks ago

Answer is correct
upvoted 1 times
  tms2020 5 months, 3 weeks ago

Yes given answer is correct
upvoted 2 times
You are building an AI system.

Which task should you include to ensure that the service meets the Microsoft transparency principle for responsible AI?
A. Ensure that all visuals have an associated text that can be read by a screen reader.
B. Enable autoscaling to ensure that a service scales based on demand.
C. Provide documentation to help developers debug code.
D. Ensure that a training dataset is representative of the population.
Correct Answer: C
Reference:
  dolphin_1923 Highly Voted  1 month ago

C is correct.
https://docs.microsoft.com/en-us/learn/modules/get-started-ai-fundamentals/7-understand-responsible-ai
upvoted 5 times

upvoted 2 times
  nott 1 month ago

C is correct
transparency tab --
https://www.microsoft.com/en-us/ai/responsible-ai?activetab=pivot1%3aprimaryr6
upvoted 2 times
  mnmcbl 2 days, 21 hours ago

A should be Inclusiveness
upvoted 1 times
  mickellman 1 month, 3 weeks ago

I think the anwser should be A.
Option A is about providing associate text to let users have well understanding on what the AI application is doing. So it is about applying
Transparency Principle.
Option C is about providing documents during developing something, that is not related any AI process. Developer is not the consumer of AI. For
me, the scenario is just a Knowledge Base.
upvoted 2 times
  PaulChimzy 3 weeks ago

This option is more about inclusiveness, ensuring the visually impaired are not left out in designing AI solutions
upvoted 1 times
  Alasco 2 months ago

AI systems should be understandable. Users should be made fully aware of the purpose of the system, how it works, and what limitations may be
expected. "Transparency"
https://docs.microsoft.com/en-us/learn/modules/get-started-ai-fundamentals/7-understand-responsible-ai
upvoted 1 times
  Lewikeezy 2 months ago

The answer is C, A is not correct here and D, but in the broad sense it could be A, C and D, but in this case the question points more to C. " you are
developing....." nothing much to account for inclusiveness so my answer is a big big C
upvoted 2 times
  Ghina 2 months, 4 weeks ago

What is the correct answer plz?! :(
upvoted 3 times

The key is "You are building an AI system", you are the developer and you have to be transparent, so answer "C" is correct.
upvoted 2 times

your transparency allows fellow developers to debug your code, makes sense?
upvoted 2 times
  Madkore23 3 months, 1 week ago

I think A is the correct answer. C is an example of reliability and safety principle.
upvoted 1 times
  Massy 3 months ago

C is transparency, you show the documentation so nothing is hide.
upvoted 1 times
  fdlsys 4 months ago

TRANSPARENCY
From the referenced URL:

A crucial part of transparency is what we refer to as intelligibility, or the useful explanation of the behavior of AI systems and their components.
Above applies to everyone using/relying on the AI system, not just developers. Question mentions screen-reader which IN ADDITION to
transparency implies INCLUSIVNESS.
upvoted 1 times
  Mainakhere 4 months, 1 week ago

Answer is "D" to ensure Fairness principle to avoid bias.
upvoted 2 times
  Whirly 5 months ago

Answer is C, to meet goals of AI transparency provide code.
upvoted 3 times

since the question states Microsoft transparency principle for responsible AI
then C is correct. if it is a general question then A
upvoted 3 times
  DarioReymago 6 months ago

is correct. the "A" is related to inclusion
upvoted 3 times

It should be (A).
The other options do not actually use AI. The only possible option where AI can be implemented is, option (A). And, those who implement this
should be transparent about the visuals and the text that matches the visual so that Speech AI can read the text.
upvoted 2 times
  Johnnien 6 months ago

One of goals of Microsoft transparency principle is to help developers to debug the AI system.
upvoted 1 times
  RzRsHt 6 months, 2 weeks ago

Microsoft transparency principle... who needs transparency
Microsoft transparency principle. who needs transparency? A developer who debugs or the average person who should not see a black box
process? It should be (A).
upvoted 2 times
  ipindado2020 6 months, 2 weeks ago

answer is correct
upvoted 4 times
DRAG DROP -
Match the types of AI workloads to the appropriate scenarios.
Select and Place:
Correct Answer:
Reference:
https://docs.microsoft.com/en-us/learn/paths/get-started-with-artificial-intelligence-on-azure/

upvoted 1 times
  Derin_tade 2 weeks, 2 days ago

Correct.
upvoted 1 times
Your company is exploring the use of voice recognition technologies in its smart home devices. The company wants to identify any barriers that
might unintentionally leave out specific user groups.
This an example of which Microsoft guiding principle for responsible AI?
A. accountability
B. fairness
C. inclusiveness
D. privacy and security
Correct Answer: C
Reference:
  Johnnien Highly Voted  6 months ago

Inclusiveness is about no one would be left out.
upvoted 8 times
  sreekarv Highly Voted  6 months, 1 week ago

Answer is correct.
Fairness is also a bit closer. But, the device is limited to home appliance. It is not for larger audience where it could go biased.
upvoted 6 times
  Jedi_sg2000 Most Recent  1 week, 1 day ago

the keyword here is "unintentionally"
-- Inclusive design practices can help system developers understand and address potential barriers in a product environment that could
unintentionally exclude people. By addressing these barriers, we create opportunities to innovate and design better experiences that benefit
everyone.
upvoted 2 times
  zubfaruq 2 weeks ago

Inclusiveness is the right answer.
Reference: https://docs.microsoft.com/en-us/learn/modules/get-started-ai-fundamentals/7-understand-responsible-ai
upvoted 1 times
  Habee6 2 weeks ago

Inclusiveness is correct
upvoted 1 times
  lakito 1 month, 4 weeks ago

imo it's fairness because inclusiveness is more about empowering everyone, while fairness is making sure that there is no bias. There does not
seem to be any empowerement here.
upvoted 1 times
  lakito 1 month, 4 weeks ago

Nevermind, after checking the microsoft learn website, I am leaning more towards inclusiveness.
upvoted 1 times

I would go with fairness since it includes users wiith special needs.
upvoted 1 times
  tearcodiac 3 months, 2 weeks ago

Answer is correct
upvoted 1 times
What are three Microsoft guiding principles for responsible AI? Each correct answer presents a complete solution.
A. knowledgeability
B. decisiveness
C. inclusiveness
D. fairness
E. opinionatedness
F. reliability and safety
Correct Answer: CDF

Reference:
  TariqNawaz 17 hours, 9 minutes ago

Answer is correct
upvoted 1 times
  Emdy 1 week, 3 days ago

correct
upvoted 2 times

upvoted 2 times
  Ajao 3 weeks, 2 days ago

The correct options are C,D,F
upvoted 1 times
  Ebenezer 1 month, 3 weeks ago

The six guiding principles are:
1. Fairness
2. Inclusiveness
3. Transparency
4. Privacy and Security
5. Reliability and Safety
6. Accountability
upvoted 4 times
  Nigihayami 1 month, 4 weeks ago

Asnwer is correct
upvoted 1 times

Answer is correct
upvoted 2 times

answer is correct
upvoted 4 times
HOTSPOT -
Hot Area:
Correct Answer:
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/concept-object-detection

Correct answer object detection
upvoted 1 times
  zubfaruq 2 weeks ago

Object Detection is the correct answer.
Reference: https://docs.microsoft.com/en-us/learn/modules/detect-objects-images-custom-vision/1-introduction
upvoted 2 times
  Habee6 2 weeks ago

Object detection is correct
upvoted 2 times
HOTSPOT -
Hot Area:
Correct Answer:
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/team-data-science-process/create-features

Feature engineering
upvoted 1 times
  akshayr2021 1 week, 4 days ago

Answer is correct
upvoted 1 times
  Forspotboy 1 week, 4 days ago

Answer is correct! https://docs.microsoft.com/en-us/azure/machine-learning/team-data-science-process/create-features
upvoted 1 times
You run a charity event that involves posting photos of people wearing sunglasses on Twitter.
You need to ensure that you only retweet photos that meet the following requirements:
✑ Include one or more faces.
✑ Contain at least one person wearing sunglasses.
What should you use to analyze the images?
A. the Verify operation in the Face service
B. the Detect operation in the Face service
C. the Describe Image operation in the Computer Vision service
D. the Analyze Image operation in the Computer Vision service
Correct Answer: B
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/face/overview

answer si correct
https://docs.microsoft.com/en-us/azure/cognitive-services/face/concepts/face-detection
Face detect can be requested to detect also glasses attribute

upvoted 6 times
  TariqNawaz Most Recent  17 hours, 4 minutes ago

It's correct answer
upvoted 1 times

Answer is correct
upvoted 4 times
Which metric can you use to evaluate a classification model?
A. true positive rate
B. mean absolute error (MAE)
C. coefficient of determination (R2)
D. root mean squared error (RMSE)
Correct Answer: A
What does a good model look like?
An ROC curve that approaches the top left corner with 100% true positive rate and 0% false positive rate will be the best model. A random model
would display as a flat line from the bottom left to the top right corner. Worse than random would dip below the y=x line.
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#classification

Correct answer is A
upvoted 1 times
  GetulioJr 1 week, 6 days ago

MAE, RMSE and R2 are metris for regression:
https://docs.microsoft.com/en-us/azure/machine-learning/algorithm-module-reference/evaluate-model
So answer is correct.
upvoted 2 times

i think its A,the idea behind confusion Matrix
upvoted 3 times

In exam 27 March
upvoted 2 times

Came in exam Feb 28
upvoted 4 times
  SSJA 4 months, 4 weeks ago

Given answer is correct - A
upvoted 2 times

AUC is the Area under the Receiver Operating Characteristic Curve. Micro is computed globally by combining the true positives and false positives
from each class.
upvoted 1 times
Which two components can you drag onto a canvas in Azure Machine Learning designer? Each correct answer presents a complete solution.
A. dataset
B. compute
C. pipeline
D. module
Correct Answer: AD
You can drag-and-drop datasets and modules onto the canvas.
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/concept-designer
  ExamTopics007 Highly Voted  6 months, 2 weeks ago

Azure Machine Learning designer lets you visually connect datasets and modules on an interactive canvas to create machine learning models.
upvoted 14 times
  dennis Highly Voted  3 months, 3 weeks ago

Answer is correct
upvoted 5 times

Answer is correct
upvoted 1 times
  Giggles_a12 4 months ago

answer is correct.
upvoted 2 times

The designer gives you a visual canvas to build, test, and deploy machine learning models. With the designer you can:
Drag-and-drop datasets and modules onto the canvas.

upvoted 3 times
You need to create a training dataset and validation dataset from an existing dataset.
Which module in the Azure Machine Learning designer should you use?
A. Select Columns in Dataset
B. Add Rows
C. Split Data
D. Join Data
Correct Answer: C
A common way of evaluating a model is to divide the data into a training and test set by using Split Data, and then validate the model on the
training data.
Use the Split Data module to divide a dataset into two distinct sets.
The studio currently supports training/validation data splits
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/how-to-configure-cross-validation-data-splits
  kumarakash Highly Voted  1 month, 2 weeks ago

C. Split Data
upvoted 5 times

Answer is correct
upvoted 1 times

Given ans is correct
upvoted 4 times

anser is correct.
upvoted 2 times

answer is correct
upvoted 3 times

https://docs.microsoft.com/en-us/azure/machine-learning/how-to-create-register-datasets
upvoted 2 times
DRAG DROP -
Match the types of machine learning to the appropriate scenarios.
To answer, drag the appropriate machine learning type from the column on the left to its scenario on the right. Each machine learning type may be
used once, more than once, or not at all.
Select and Place:
Correct Answer:
Box 1: Regression -
In the most basic sense, regression refers to prediction of a numeric target.
Linear regression attempts to establish a linear relationship between one or more independent variables and a numeric outcome, or dependent
variable.
You use this module to define a linear regression method, and then train a model using a labeled dataset. The trained model can then be used
to make predictions.
Box 2: Clustering -
Clustering, in machine learning, is a method of grouping data points into similar clusters. It is also called segmentation.
Over the years, many clustering algorithms have been developed. Almost all clustering algorithms use the features of individual items to find
similar items. For example, you might apply clustering to find similar people by demographics. You might use clustering with text analysis to
group sentences with similar topics or sentiment.
Box 3: Classification -
Two-class classification provides the answer to simple two-choice questions such as Yes/No or True/False.
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/linear-regression
  ashayk Highly Voted  8 months, 2 weeks ago

The answer is wrong for point no 2 and 3.
It is clear in the comments provided below:
Clustering is unsupervised learning technique about grouping similar variables together. the answer should be clustering.
third, predict whether -- this is clear classification problem.
upvoted 55 times
  jackreacher Highly Voted  8 months, 1 week ago

2nd one should be clustering, 3rd one should be classification
upvoted 41 times
  AshishScotia Most Recent  2 weeks, 3 days ago

upvoted 1 times
  Babuni 1 month ago

Segment Customers into different groups to support a marketing initiative: Clustering
Predict whether or not a student will complete a university course: Classification
upvoted 1 times
  spykidXX 1 month ago

segment into groups = clustering
prediction = regression
upvoted 1 times

Regression, clustering and classification
upvoted 2 times
  Chinnathala 1 month, 1 week ago

Correct Answers are :-
1- Regression
2- Clustering
3- Classification
upvoted 4 times
  AmiraBedhiafi 1 month, 3 weeks ago

1- Regression
2- Clustering
3- Classification
upvoted 8 times
  Shammy45 1 month, 4 weeks ago

regression , Clustering , Classification
upvoted 2 times

Answer is 1.Regression, 2.Clustering and 3.Classification
upvoted 6 times
  vmontalvao 3 months ago

You don't need to use all available possibilities and you can use one more than once. For predictions you use Regression type so this is my answer:
1. Regression
2. Clustering
3. Regression
upvoted 1 times

The third is classification, you have to predict "pass" or "not pass". It would be regression if the goal was to predict the exam grade
upvoted 4 times

Yeah, I've reviewed and you are right. It's a boolean answer so definitively Classification for the 3rd one. Apologizes if I've mislead somebody.
upvoted 4 times

Came in exam Feb 28
upvoted 2 times
  mlaus 2 months, 1 week ago

Do you know the right answer?
upvoted 1 times

2nd should be Clustering: Keywords Segment and different groups. As classes are unknown here, the Classification is not applicable but un-
supervised Clustering fits most.
3rd Classification: Classes are either 'yes' or 'no' so it must be classification.
upvoted 1 times

Answer should be Regression - Clustering - Classification
upvoted 2 times

Answer is Regression - Clustering - Classification
upvoted 2 times
  ziouan 3 months, 4 weeks ago

g
upvoted 1 times

I think the answers are 1st Regression, 2nd Clustring, 3rd Classification.
upvoted 1 times
DRAG DROP -
Match the machine learning tasks to the appropriate scenarios.
To answer, drag the appropriate task from the column on the left to its scenario on the right. Each task may be used once, more than once, or not
at all.
Select and Place:
Correct Answer:
Box 1: Model evaluation -

The Model evaluation module outputs a confusion matrix showing the number of true positives, false negatives, false positives, and true
negatives, as well as
ROC, Precision/Recall, and Lift curves.
Box 2: Feature engineering -

Feature engineering is the process of using domain knowledge of the data to create features that help ML algorithms learn better. In Azure
Machine Learning, scaling and normalization techniques are applied to facilitate feature engineering. Collectively, these techniques and feature
engineering are referred to as featurization.
Note: Often, features are created from raw data through a process of feature engineering. For example, a time stamp in itself might not be
useful for modeling until the information is transformed into units of days, months, or categories that are relevant to the problem, such as
holiday versus working day.
Box 3: Feature selection -

In machine learning and statistics, feature selection is the process of selecting a subset of relevant, useful features to use in building an
analytical model. Feature selection helps narrow the field of data to the most valuable inputs. Narrowing the field of data helps reduce noise
and improve training performance.
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/studio/evaluate-model-performance https://docs.microsoft.com/en-
us/azure/machine-learning/concept-automated-ml

answer is correct
upvoted 9 times
  Kanjati Most Recent  1 month ago

The answer is correct

upvoted 1 times

answer is correct
upvoted 1 times

In exam 27 March
upvoted 2 times

The first two answers seems correct to me but I think the last one is Model Training and not Feature Selection.
upvoted 1 times

You are choosing the features, so it's feature selection
upvoted 3 times

anwer is correct.
upvoted 1 times
HOTSPOT -
Hot Area:
Correct Answer:
Reference:
https://www.baeldung.com/cs/feature-vs-label
https://machinelearningmastery.com/discover-feature-engineering-how-to-engineer-features-and-how-to-get-good-at-it/

Answer is Features
upvoted 70 times
  Mahesh_mm Highly Voted  8 months, 1 week ago

Features is right answer
upvoted 14 times
  Babuni Most Recent  1 month ago

Feature selection and engineering directly impact the predicted labels.
Answer should be Features.
upvoted 2 times

features
upvoted 1 times

features! a result is a label
upvoted 1 times
  PGG 1 month, 1 week ago

Tricky one, all features must be dependant variables for the labeled data. So more correct answer will be A, as not all Features add value to
prediction. That's why you have a module for Feature Selection...maybe I will choose A over B
upvoted 1 times

Features are independent variables. The labels depend on the Features which makes them the dependent variable..
The independent variables are the features which occur freely.

upvoted 1 times

Features
upvoted 1 times

features is ok
upvoted 1 times

should be Features
upvoted 1 times
  amyxiang 2 months, 2 weeks ago

Agree with features
upvoted 2 times
  htolajide 3 months ago

Feature should be the right since the model will have to use feature an compare with label to predict a result
upvoted 3 times

Answer if features
upvoted 1 times

Data values that influence the prediction: The feature columns influence the prediction. The feature columns are also called as
Predictors/Independent variables while actual predictions are called as Dependent variable/label.
upvoted 3 times
  lvbranco 3 months, 3 weeks ago

is Features
upvoted 1 times
  kumar123 3 months, 4 weeks ago

Its a tricky question. Data used for model prediction are called features and data value which influence the model are called label. So my vote is for
label.
upvoted 6 times
  dhnguyen 3 months, 4 weeks ago

The term 'influence' is misleading in the statement. It should be 'enable' . Then the correct answer is "labels" for annoted data
upvoted 3 times
  ziouan 3 months, 4 weeks ago

Answer is Features
upvoted 1 times
You have the Predicted vs. True chart shown in the following exhibit.
Which type of model is the chart used to evaluate?
A. classification
B. regression
C. clustering
Correct Answer: B
What is a Predicted vs. True chart?
Predicted vs. True shows the relationship between a predicted value and its correlating true value for a regression problem. This graph can be
used to measure performance of a model as the closer to the y=x line the predicted values are, the better the accuracy of a predictive model.
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-m
  htolajide Highly Voted  3 months ago

Correct answer is provided
upvoted 5 times

Answer is correct
upvoted 1 times
  rochester 3 months, 1 week ago

Correct answer
upvoted 3 times

Regression is correct
upvoted 3 times

answer is correct
upvoted 1 times

correct
upvoted 3 times
Which type of machine learning should you use to predict the number of gift cards that will be sold next month?
A. classification
B. regression
C. clustering
Correct Answer: B
variable.
Reference:
  kprasha4 Highly Voted  8 months, 2 weeks ago

Answer should be B.
upvoted 69 times
  bala1 Highly Voted  8 months, 2 weeks ago

Answer is B
upvoted 18 times
  Ati1362 Most Recent  1 week, 4 days ago

B is correct
upvoted 2 times

B is the right answer
upvoted 1 times

Here we are predicting a numeric label. (No of Gift Cards)
Answer should be Regression.
upvoted 1 times

predicting numerical values = regression
upvoted 2 times

Regression has something to do with numerical values!
upvoted 3 times
  Daves2ng 1 month, 1 week ago

I believe this answer should be B. even the description and explanation given suggest B is correct answer
upvoted 1 times
  SyedAunZaidi 1 month, 1 week ago

Answer is B, regression
upvoted 2 times
  Brahmin99 2 months ago

Answer should be B.
upvoted 1 times
  Zeemani 2 months, 1 week ago

Ans = B
upvoted 1 times

should be regression
upvoted 1 times

B is correct.
upvoted 1 times
  Kishorepi 2 months, 2 weeks ago

Answer should be B as it is predicting number.
upvoted 2 times
  Uzor 2 months, 2 weeks ago

Should be regression
upvoted 1 times

Should be Regression
upvoted 1 times
  ManojMittal 2 months, 3 weeks ago

This question set has a lot of mistakes in answers - (with all due respect) probably the maker of this is not so good in AI concepts.
upvoted 4 times
You have a dataset that contains information about taxi journeys that occurred during a given period.
You need to train a model to predict the fare of a taxi journey.
What should you use as a feature?
A. the number of taxi journeys in the dataset
B. the trip distance of individual taxi journeys
C. the fare of individual taxi journeys
D. the trip ID of individual taxi journeys
Correct Answer: B
The label is the column you want to predict. The identified Featuresare the inputs you give the model to predict the Label.
Example:
The provided data set contains the following columns:
vendor_id: The ID of the taxi vendor is a feature.
rate_code: The rate type of the taxi trip is a feature.
passenger_count: The number of passengers on the trip is a feature. trip_time_in_secs: The amount of time the trip took. You want to predict
the fare of the trip before the trip is completed. At that moment, you don't know how long the trip would take. Thus, the trip time is not a feature
and you'll exclude this column from the model. trip_distance: The distance of the trip is a feature. payment_type: The payment method (cash or
credit card) is a feature. fare_amount: The total taxi fare paid is the label.
Reference:
https://docs.microsoft.com/en-us/dotnet/machine-learning/tutorials/predict-prices
  Grewal Highly Voted  7 months, 1 week ago

B is correct
upvoted 30 times
  maddy07 Highly Voted  6 months, 3 weeks ago

C is label and B is the feature.
upvoted 10 times

Answer is correct
upvoted 1 times
  PhillipH 3 weeks, 3 days ago

B is correct
upvoted 1 times

the price is a label and distance is a feature!
upvoted 2 times

C is label and B is the feature for me
upvoted 1 times
  Az900Exam2021 4 months ago

B is correct. feature is input and label is output.
upvoted 1 times
  n1a2m3e3 5 months, 2 weeks ago

B is correct
upvoted 1 times
  Panos11 6 months, 1 week ago

Some people got confused here. The answer displayed is correct (B)
Remember regression / predictions follow this principle - y = beta_0 + beta_1 * variable_1
Now what is your dependent variable? the outcome in other words. Fares so Y is the fares
Now what information you are going to use to predict this? variable
One variable that affect the fare is the distance, so variable_1 =distance.
So the answer you are looking for is distance.
upvoted 5 times
  Raja3sa 6 months, 1 week ago

Answer B
upvoted 2 times

B is correct.
upvoted 4 times
  fatrapb1t 6 months, 3 weeks ago

B is correct. C is the label (target)
upvoted 8 times
  jasonma 7 months ago

I think the answer is C. If you choose B, you still don't have the unit price to calculate the whole journey cost.
upvoted 3 times
  lollo1234 3 months, 2 weeks ago

It is also descripted in the ML .NET Tutorial description.
The label is the column you want to predict. When performing a regression task, the goal is to predict a numerical value. In this price prediction
scenario, the cost of a taxi ride is being predicted. Therefore, the fare_amount is the label. The identified features are the inputs you give the
model to predict the label. In this case, the rest of the columns with the exception of trip_time_in_secs are used as features or inputs to predict
the fare amount.
https://docs.microsoft.com/en-us/dotnet/machine-learning/tutorials/predict-prices-with-model-builder
upvoted 3 times
  abraham_10 6 months, 3 weeks ago

Yeah. But the question is "What should you use as a feature ?" C is a label
upvoted 8 times
  AmarBen 7 months, 1 week ago

C. the fare of individual taxi journeys is the correct answer
upvoted 3 times

it is in function of the distance, the individual journeys is relate to the km in thes journey
upvoted 5 times
You need to predict the sea level in meters for the next 10 years.
Which type of machine learning should you use?
A. classification
B. regression
C. clustering
Correct Answer: B
variable.
Reference:
  VT100 3 weeks, 6 days ago

Answer is regression.
upvoted 2 times

Predicting numerical values without a yes or no is regression
upvoted 4 times
  Ihueghian 1 month, 2 weeks ago

B, regression-forecasting
upvoted 3 times
  mlaus 2 months, 1 week ago

B is correct, you have to predict a value.
upvoted 2 times

In exam 27 March
upvoted 2 times

Answer is correct
upvoted 1 times
  Alseanna_24 3 months, 1 week ago

Regression
upvoted 1 times

Came in exam Feb 28
upvoted 2 times
  Tavwo 3 months, 3 weeks ago

B is correct
upvoted 1 times

The answer is Regression.
upvoted 1 times
  more765 4 months, 3 weeks ago

yes B is right
upvoted 2 times

answer is correct
upvoted 4 times
HOTSPOT -
Hot Area:
Correct Answer:
Box 1: Yes -
Automated machine learning, also referred to as automated ML or AutoML, is the process of automating the time consuming, iterative tasks of
machine learning model development. It allows data scientists, analysts, and developers to build ML models with high scale, efficiency, and
productivity all while sustaining model quality.
Box 2: No -
Box 3: Yes -
During training, Azure Machine Learning creates a number of pipelines in parallel that try different algorithms and parameters for you. The
service iterates through
ML algorithms paired with feature selections, where each iteration produces a model with a training score. The higher the score, the better the
model is considered to "fit" your data. It will stop once it hits the exit criteria defined in the experiment.
Box 4: No -
Apply automated ML when you want Azure Machine Learning to train and tune a model for you using the target metric you specify.
The label is the column you want to predict.
Reference:
https://azure.microsoft.com/en-us/services/machine-learning/automatedml/#features
  Azurite Highly Voted  3 months, 2 weeks ago

Came in exam Feb 28 AS-IS
upvoted 9 times

Answer is correct
upvoted 7 times
  narendra399 Most Recent  1 month, 3 weeks ago

Thanks for answering
upvoted 2 times
HOTSPOT -
Hot Area:
Correct Answer:

this is wrong. the answer should be C- classification as the the prediction whether the loan will be repaid or not -- whether means class -
categorical asnwer as yes or no - hence clasification
upvoted 56 times
  AliceDarling Highly Voted  8 months, 1 week ago

Correct answer is "A" I am a data Scientist & 100% sure
upvoted 49 times

I really want to know why is it regression, and not classification
upvoted 1 times
  NeerajGupta 2 months ago

Dear Data Scientist, Question is asking whether loan will be repaid or not, which signifies classification not regression.
upvoted 4 times
  AAwaad 2 months ago

AliceDarling did say that "A" - Classification which is right, don't confuse others by repeating his answer different way.
upvoted 11 times
  PC_ATL 3 months, 2 weeks ago

hahahahaha
upvoted 7 times
  paulien 7 months, 1 week ago

You don't need to be a scientist to know that for sure ;-)
upvoted 16 times
  Narasingha 6 months, 2 weeks ago

but my friend it is Classification. Read and comment
upvoted 3 times
  SnowCheetah Most Recent  1 week, 4 days ago

Since the problem want to be determine customer can be repaid loan or not. The solution would like to answer as a Yes/No. Thus the answer
should be Classification.
upvoted 1 times

Simple Yes or No Problem for the Bank.
Classification Algorithm should be used.
upvoted 1 times
  BankZenith 1 month ago

Classification is right
upvoted 1 times

Classification is Yes Paid or Not Paid the predicted value is not numerical so regression is out
upvoted 1 times

Its classification
upvoted 2 times
  Dimejidmj 2 months ago

The answer is classification
upvoted 1 times
  Zeemani 2 months, 1 week ago

CLASSIFICATION
upvoted 2 times
  mesutgan 2 months, 2 weeks ago

A classification
upvoted 1 times

should be classification
upvoted 1 times
  Matech 2 months, 2 weeks ago

Classification is actually the right answer
upvoted 1 times
  aliounegdiop 3 months ago

it s classification because the question does not mentionned a rate but whether the loan will be repaid so a possibility or not....binmary
classification with 02 possibilities 1 for yes and 0 for no
upvoted 2 times

Answer is Classification
upvoted 1 times

The answer is Classification
upvoted 2 times
  vijaysmail84 4 months, 1 week ago

A is the correct ans
upvoted 1 times

Correct Answer is Classification.
upvoted 1 times
HOTSPOT -
Hot Area:
Correct Answer:
Box 1: Yes -
In machine learning, if you have labeled data, that means your data is marked up, or annotated, to show the target, which is the answer you want
your machine learning model to predict.
In general, data labeling can refer to tasks that include data tagging, annotation, classification, moderation, transcription, or processing.
Box 2: No -
Box 3: No -
Accuracy is simply the proportion of correctly classified instances. It is usually the first metric you look at when evaluating a classifier.
However, when the test data is unbalanced (where most of the instances belong to one of the classes), or you are more interested in the
performance on either one of the classes, accuracy doesn't really capture the effectiveness of a classifier.
Reference:
https://www.cloudfactory.com/data-labeling-guide
https://docs.microsoft.com/en-us/azure/machine-learning/studio/evaluate-model-performance

Answer is correct.
Note points:
--'labels' are the outputs(ie we map each set of features to a 'label')
--recall and precision are other imp metrics in a classification problem(other than Accuracy)
upvoted 15 times
  ealcober Highly Voted  7 months, 3 weeks ago

I think the first would be FEATURING (feature is input, label is output)
upvoted 5 times

upvoted 1 times

i think its Y/N/Y
upvoted 2 times
  caniculus 3 months, 2 weeks ago

Answer is correct.
Regression has labels and features.

Machine Learning has labeling.
https://labelyourdata.com/articles/what-is-data-labeling-in-machine-learning/
"A label or a tag is simply an identifying element that explains what a piece of data is."
upvoted 1 times

Came in exam Feb 28
upvoted 2 times

1°) is ok:
https://aws.amazon.com/es/sagemaker/groundtruth/what-is-data-labeling/
upvoted 2 times
Which service should you use to extract text, key/value pairs, and table data automatically from scanned documents?
A. Form Recognizer
B. Text Analytics
C. Ink Recognizer
D. Custom Vision
Correct Answer: A
Accelerate your business processes by automating information extraction. Form Recognizer applies advanced machine learning to accurately
extract text, key/ value pairs, and tables from documents. With just a few samples, Form Recognizer tailors its understanding to your
documents, both on-premises and in the cloud. Turn forms into usable data at a fraction of the time and cost, so you can focus more time
acting on the information rather than compiling it.
Reference:
https://azure.microsoft.com/en-us/services/cognitive-services/form-recognizer/
  Donny_Slim Highly Voted  3 months, 1 week ago

Given answer (Form Recognizer) is correct.
upvoted 13 times
  Ajao Most Recent  1 month ago

Form recognizer is the correct answer
upvoted 2 times

Form Recognizer is correct answer.
upvoted 1 times

Form Recognizer supports automated document processing through:
A pre-built receipt model that is provided out-of-the-box, and is trained to recognize and extract data from sales receipts.
Custom models, which enable you to extract what are known as key/value pairs and table data from forms. Custom models are trained using your
own data, which helps to tailor this model to your specific forms. Starting with only five samples of your forms, you can train the custom model.
After the first training exercise, you can evaluate the results and consider if you need to add more samples and re-train.
upvoted 1 times

Form Recognizer...."A more advanced OCR scenario is the extraction of information from forms, such as purchase orders or invoices, with a
semantic understanding of what the fields in the form represent. The Form Recognizer service is specifically designed for this kind of AI problem."
upvoted 2 times
  SAANCODE 2 months, 4 weeks ago

Form Analytics is the correct answer
upvoted 2 times

I think it's Text Analytics
upvoted 1 times

Given answer is correct.
upvoted 1 times

a is ok
upvoted 3 times
HOTSPOT -
Hot Area:
Correct Answer:
Accelerate your business processes by automating information extraction. Form Recognizer applies advanced machine learning to accurately
extract text, key/ value pairs, and tables from documents. With just a few samples, Form Recognizer tailors its understanding to your
documents, both on-premises and in the cloud. Turn forms into usable data at a fraction of the time and cost, so you can focus more time
acting on the information rather than compiling it.
Reference:
  Abdulwasiu Highly Voted  2 months, 2 weeks ago

answer is correct
upvoted 5 times
  heyshomy Most Recent  2 months, 2 weeks ago

Correct answer
upvoted 1 times

In exam 27 March
upvoted 3 times

Came in exam Feb 28
upvoted 4 times

answer is correct
upvoted 3 times
You use Azure Machine Learning designer to publish an inference pipeline.

Which two parameters should you use to consume the pipeline? Each correct answer presents part of the solution.
A. the model name
B. the training endpoint
C. the authentication key
D. the REST endpoint
Correct Answer: CD
You can consume a published pipeline in the Published pipelines page. Select a published pipeline and find the REST endpoint of it.
To consume the pipeline, you need:
✑ The REST endpoint for your service
✑ The Primary Key for your service
Reference:
https://docs.microsoft.com/en-in/learn/modules/create-regression-model-azure-machine-learning-designer/deploy-service

I think C&D are answers
upvoted 62 times
  RSSRAO Highly Voted  8 months ago

Test the service
Now you can test your deployed service from a client application - in this case, you'll use the code in the cell below to simulate a client application.
1. On the Endpoints page, open the predict-auto-price real-time endpoint.
2. When the predict-auto-price endpoint opens, view the Consume tab and note the following information there. You need this to connect to your
deployed service from a client application.
o The REST endpoint for your service
o The Primary Key for your service
upvoted 15 times
  gargaditya 7 months, 2 weeks ago

above text is described at https://docs.microsoft.com/en-in/learn/modules/create-regression-model-azure-machine-learning-designer/deploy-
service
so answer is C,D
upvoted 12 times
  Ashish_09 Most Recent  3 weeks, 2 days ago

You can find the REST endpoint of a pipeline endpoint in the run overview panel. By calling the endpoint, you are consuming its default published
pipeline.
To make a REST call, you will need an OAuth 2.0 bearer-type authentication header
Hence C and D should be the answer.
Source: https://docs.microsoft.com/en-us/azure/machine-learning/how-to-run-batch-predictions-designer
upvoted 2 times

REST End Point and Authentication Key are needed to deploy the model as a Service to Customers. C and D are correct answers to this question.
upvoted 1 times

C&D are correct
upvoted 1 times
  deveast 1 month, 1 week ago

C & D are the correct answers
upvoted 2 times

C & D should be correct answer
upvoted 1 times
  fit_muscle_boy 1 month, 2 weeks ago

Yes, CD are correct answers
upvoted 1 times

C & D is ok
upvoted 1 times
  captain_nemo 2 months, 1 week ago

REST Endpoint and Auth Key
upvoted 1 times
  apartha77 2 months, 3 weeks ago

C & D for me
upvoted 1 times

Answer is C and D
upvoted 1 times

I would say A, C and D but it says to chose only 2.
"To use your model, client application developers need the following information:
• Project ID: The unique ID of the Custom Vision project you created to train the model.
• Model name: The name you assigned to the model during publishing.
• Prediction endpoint: The HTTP address of the endpoints for the prediction resource to which you published the model (not the training resource).
• Prediction key: The authentication key for the prediction resource to which you published the model (not the training resource)."
upvoted 4 times

Authentication Key and REST endpoint is correct
upvoted 2 times
  psdinesh 4 months ago

It should be C & D
upvoted 1 times
  zic04 4 months, 1 week ago

C & D for me
upvoted 1 times
  kapilsri 4 months, 4 weeks ago

https://thenewstack.io/tutorial-create-training-and-inferencing-pipelines-with-azure-ml-designer/ -- This explains very well. it has to be REST end
point and Authentication key
upvoted 5 times
HOTSPOT -
Hot Area:
Correct Answer:
To perform real-time inferencing, you must deploy a pipeline as a real-time endpoint.

Real-time endpoints must be deployed to an Azure Kubernetes Service cluster.
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/concept-designer#deploy
  RSSRAO Highly Voted  8 months ago

Correct. For Prod - AKS and for Dev/Test - use Azure Container Service
upvoted 21 times
  captain_nemo 2 months, 1 week ago

Where is this given?
the tutorials made us deploy to Azure Container Service
upvoted 2 times
  Ash111 Most Recent  2 months, 1 week ago

given ans is correct
upvoted 1 times

Correct:
To perform real-time inferencing, you must deploy a pipeline as a real-time endpoint. The real-time endpoint creates an interface between an
external application and your scoring model. A call to a real-time endpoint returns prediction results to the application in real-time. To make a call
to a real-time endpoint, you pass the API key that was created when you deployed the endpoint. The endpoint is based on REST, a popular
architecture choice for web programming projects.
Real-time endpoints must be deployed to an Azure Kubernetes Service cluster.

upvoted 4 times
HOTSPOT -
Hot Area:
Correct Answer:

variable.
Incorrect Answers:
✑ Classification is a machine learning method that uses data to determine the category, type, or class of an item or row of data.
✑ Clustering, in machine learning, is a method of grouping data points into similar clusters. It is also called segmentation.
Over the years, many clustering algorithms have been developed. Almost all clustering algorithms use the features of individual items to find
similar items. For example, you might apply clustering to find similar people by demographics. You might use clustering with text analysis to
group sentences with similar topics or sentiment.
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/algorithm-module-reference/linear-regression https://docs.microsoft.com/en-
us/azure/machine-learning/studio-module-reference/machine-learning-initialize-model-clustering
  naimul Highly Voted  1 month, 1 week ago

correct
upvoted 5 times
  fit_muscle_boy Most Recent  1 month, 2 weeks ago

Regression is the correct answer
upvoted 2 times
  iffah 1 month, 2 weeks ago

correct
upvoted 1 times

correct
upvoted 1 times

In exam 27 March
upvoted 2 times

Definitely C
upvoted 1 times
  SAANCODE 2 months, 4 weeks ago

corrrect
upvoted 1 times

Came in exam Feb 28
upvoted 2 times
  sabita 3 months, 2 weeks ago

correct
upvoted 1 times

answer is correct, regression
upvoted 2 times

answer is correct
upvoted 1 times
HOTSPOT -
Hot Area:
Correct Answer:
Box 1: Yes -
Azure Machine Learning designer lets you visually connect datasets and modules on an interactive canvas to create machine learning models.
Box 2: Yes -
With the designer you can connect the modules to create a pipeline draft.
As you edit a pipeline in the designer, your progress is saved as a pipeline draft.
Box 3: No -
Reference:
  Massy Highly Voted  3 months, 1 week ago

It's correct, you can customize but only using Python and R code.
upvoted 10 times

answer is correct
upvoted 10 times
  Alivina Most Recent  2 months, 3 weeks ago

A similar question come:
Azure Machine Learning Designer enables you to include custom Python functions. (YES)
upvoted 8 times

thanks
upvoted 1 times

Came in exam Feb 28
upvoted 4 times
HOTSPOT -
You have the following dataset.
You plan to use the dataset to train a model that will predict the house price categories of houses.
What are Household Income and House Price Category? To answer, select the appropriate option in the answer area.
Hot Area:
Correct Answer:
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/studio/interpret-model-results

answer is correct
upvoted 9 times
  Joe75 Most Recent  2 weeks, 5 days ago

correct. Feature = Input. Label = Output.
upvoted 3 times

House Price Category is the output space or the label.The answer is correct
upvoted 1 times
  leecirca05 1 month, 3 weeks ago

thank you
upvoted 1 times

https://docs.microsoft.com/en-us/azure/machine-learning/studio/interpret-model-results
upvoted 4 times
HOTSPOT -
Hot Area:
Correct Answer:
Reference:
  Test1992 1 week, 6 days ago

Correct
upvoted 1 times
HOTSPOT -
Hot Area:
Correct Answer:
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/how-to-designer-python https://docs.microsoft.com/en-us/azure/machine-
learning/concept-automated-ml
  giga_space 5 days, 11 hours ago

yes/yes/no
upvoted 1 times
  vishnukumartr 6 days, 11 hours ago

It should be Yes / Yes / No
upvoted 1 times
  bapu2020 6 days, 19 hours ago

I think third is incorrect. Answer should be false. Azure machine learning designer has canvas.
upvoted 1 times
A medical research project uses a large anonymized dataset of brain scan images that are categorized into predefined brain haemorrhage types.
You need to use machine learning to support early detection of the different brain haemorrhage types in the images before the images are
reviewed by a person.
This is an example of which type of machine learning?
A. clustering
B. regression
C. classification
Correct Answer: C
Reference:
https://docs.microsoft.com/en-us/learn/modules/create-classification-model-azure-machine-learning-designer/introduction
  paulien Highly Voted  5 months, 4 weeks ago

the brain haemorrhage types are predefined (labeled), so it's classification
upvoted 27 times
  Larry99 Highly Voted  6 months, 1 week ago

No it is definetly C
upvoted 9 times
  Nilzuka 6 months ago

Yes or No following results so indeed, it's C.
upvoted 3 times
  RaulDuke 5 months, 4 weeks ago

Read the question carefully. It's not Yes or No question. It is do differ types of brain hemorrhage. So correct answer (in my opinion 100%) is:
A - Clustering.
upvoted 10 times
  GetulioJr Most Recent  2 weeks ago

Clustering you define how many clusters you want, not types. Type you are classifying, not separating data.
upvoted 1 times
  BankZenith 3 weeks, 3 days ago

We know pre define type so it should be classification
upvoted 1 times
  rakelcoelho 3 weeks, 4 days ago

I think is clustering for 2 reason:
1- The question says "before the images are reviewed by a person", so this should use an unsupervised learning method
2- the question also says "brain haemorrhage types", so it doesn't seem an yes/no question
upvoted 2 times

For the 2nd reason there is something called multi classification. Doesn't always have to be yes/no
upvoted 2 times
  xcelerent 1 month, 3 weeks ago

Clustering is an unsupervised learning method whereas classification is a supervised learning method.
upvoted 1 times
  HS9147 1 month, 4 weeks ago

Multiple Classification is a kind of classifation.
upvoted 3 times

For sure it is not classification. It clearly states you will need to match the image to a specific image group with is created by the medical research
project. So this is not a YES/NO response. More of which group the image falls in e.g. Stage 1, Stage 2, Stage 3 etc.
upvoted 3 times
  Taiwoswot 2 months ago

The answer is clustering (A): Because the question requested that we're to design a system for early detection. So it's not a yes or no thing. In other
words, it's asking that we categorize the images. So in my opinion, it's clustering.
upvoted 2 times
  tosky 2 months, 4 weeks ago

Classification
The dataset has been predefined (hence model gets trained). The model then group the large dataset base on the predefined groups(types)
thereby helping the medical team to simply review each group and making their work easy.
upvoted 3 times

It is classification. the key terms here are "categorized", "predefined" = labels, and "types" = group, which could easily be be confused for clusters,
however the context here matters.
upvoted 1 times
  bekosg 3 months, 3 weeks ago

I think that the case here is that we have some millions of data records ("large dataset"), clustered into a few haemorrhage types (can' t be millions
i believe..). Therefore, i would go with A clustering.
upvoted 2 times
  rsseyouri 3 months, 3 weeks ago

They are predefined types therefore C is the correct answer
upvoted 3 times
  JIep4uk 3 months, 3 weeks ago

Classification is correct!
upvoted 4 times
  DennisWitjes 4 months ago

Correct answer is C. It mentions PREDEFINED categories, which means it's supervised due to the labelled data aspect.
upvoted 4 times
  Haisen 4 months, 1 week ago

It is C classification. See" into predefined brain haemorrhage types" since the brain haemorrhage types is predefined, then it is classification. If it is
undefined/unknown, it will be clustering.
upvoted 4 times
  DanielGP 4 months ago

I agree with this comment and I would add that this is actually a "multi-class" Classification case.
upvoted 2 times
  iolkenny 4 months, 4 weeks ago

Should be A - clustering
Because this needs support "early detection of the different brain haemorrhage types" so you don't know what to classify yet.
And this is what's in Microsoft Docs
"Clustering is often used for exploration of data prior to analysis with other more predictive algorithms"
https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/machine-learning-initialize-model-clustering
upvoted 5 times
When training a model, why should you randomly split the rows into separate subsets?
A. to train the model twice to attain better accuracy
B. to train multiple models simultaneously to attain better performance
C. to test the model by using data that was not used to train the model
Correct Answer: C
  jurimec Highly Voted  3 months, 2 weeks ago

this is the famous 70% & 30%?
upvoted 10 times

yes it is
upvoted 4 times

Answer is correct
upvoted 1 times
  Denbulz 1 week, 3 days ago

Answer is correct so the data used in training a model is not static or needed to be set manually.
upvoted 1 times
  AcidAttack 1 month ago

correct
upvoted 1 times
  Ajao 2 months ago

First for training then evaluation. The given answer is correct.
upvoted 2 times

answer is correct
upvoted 2 times

answer is correct
upvoted 4 times
You are evaluating whether to use a basic workspace or an enterprise workspace in Azure Machine Learning.
What are two tasks that require an enterprise workspace? Each correct answer presents a complete solution.
A. Use a graphical user interface (GUI) to run automated machine learning experiments.
B. Create a compute instance to use as a workstation.
C. Use a graphical user interface (GUI) to define and run machine learning experiments from Azure Machine Learning designer.
D. Create a dataset from a comma-separated value (CSV) file.
Correct Answer: AC
Note: Enterprise workspaces are no longer available as of September 2020. The basic workspace now has all the functionality of the enterprise
workspace.
Reference:
https://www.azure.cn/en-us/pricing/details/machine-learning/
https://docs.microsoft.com/en-us/azure/machine-learning/concept-workspace
  Nilzuka Highly Voted  6 months ago

This question should not be present in future exams as Enterprise workspace is now fused with Basic. Someone please follow up on this.
upvoted 17 times

thats true
upvoted 1 times
  DarioReymago Highly Voted  5 months, 4 weeks ago

I passed the exam yesterday, I found this question
upvoted 5 times
  BethelGold 2 weeks, 1 day ago

is the answer correct?
upvoted 2 times
  nohaph Most Recent  5 months, 2 weeks ago

They can ask about it until the end of 2020:
Beginning December 21st, all Enterprise Edition workspaces will be automatically set to Basic Edition, which has the same capabilities. No
downtime will occur during this process. On January 1, 2021, Enterprise Edition will be formally retired.
In either editions, customers are responsible for the costs of Azure resources consumed and will not need to pay any additional charges for Azure
Machine Learning.
upvoted 4 times
You need to predict the income range of a given customer by using the following dataset.
Which two fields should you use as features? Each correct answer presents a complete solution.
A. Education Level
B. Last Name
C. Age
D. Income Range
E. First Name
Correct Answer: AC
First Name, Last Name, Age and Education Level are features. Income range is a label (what you want to predict). First Name and Last Name
are irrelevant in that they have no bearing on income. Age and Education level are the features you should use.
  Denbulz 1 week, 3 days ago

The answer is correct but the used example is a little biased for me.
upvoted 1 times
  Ati1362 1 week, 5 days ago

answer is correct
upvoted 1 times
You are building a tool that will process your company‫ג‬€™s product images and identify the products of competitors.
The solution will use a custom model.
Which Azure Cognitive Services service should you use?
A. Custom Vision
B. Form Recognizer
C. Face
D. Computer Vision
Correct Answer: A
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/overview

answer is correct
upvoted 3 times
DRAG DROP -
Match the facial recognition tasks to the appropriate questions.
To answer, drag the appropriate task from the column on the left to its question on the right. Each task may be used once, more than once, or not
at all.
Select and Place:
Correct Answer:
Box 1: verification -
Face verification: Check the likelihood that two faces belong to the same person and receive a confidence score.
Box 2: similarity -
Box 3: Grouping -
Box 4: identification -
Face detection: Detect one or more human faces along with attributes such as: age, emotion, pose, smile, and facial hair, including 27
landmarks for each face in the image.
Reference:
https://azure.microsoft.com/en-us/services/cognitive-services/face/#features
  Vanshhh123 1 day, 21 hours ago

right answer
upvoted 2 times
  poo12 1 week ago

Right Answer
upvoted 2 times

upvoted 4 times

Correct.
Do two images of a face belong to the same person? This defines verification.
Does this person look like other people? This defines similarity.
Do all of these faces belong together? This defines grouping.
Who is this person in this group of people? This defines identification.
https://docs.microsoft.com/en-us/learn/modules/identify-faces-with-computer-vision/4-overview-of-face-recognition
upvoted 3 times

Correct answer
upvoted 2 times

I think the answer is correct.
upvoted 2 times

upvoted 3 times

~Face verification:
The Verify API does an authentication against two detected faces or from one detected face to one person object. Practically, it evaluates whether
two faces belong to the same person.
~Person identification:
The Identify API is used to identify a detected face against a database of people (facial recognition search). This feature might be useful for
automatic image tagging in photo management software. You create the database in advance, and you can edit it over time.
upvoted 4 times

~Find similar faces:
The Find Similar API does face matching between target face and a set of candidate faces, finding a smaller set of faces that look similar to the
target face. This is useful for doing a face search by image.
Two working modes, matchPerson and matchFace, are supported. The matchPerson mode returns similar faces after filtering for the same person
by using the Verify API. The matchFace mode ignores the same-person filter. It returns a list of similar candidate faces that may or may not belong
to the same person.
~Face grouping:
The Group API divides a set of unknown faces into several groups based on similarity. Each group is a disjoint proper subset of the original set of
faces. All of the faces in a group are likely to belong to the same person. There can be several different groups for a single person. The groups are
differentiated by another factor, such as expression, for example.
upvoted 4 times

https://docs.microsoft.com/en-us/azure/cognitive-services/face/overview
upvoted 3 times
DRAG DROP -
Match the types of computer vision workloads to the appropriate scenarios.
Select and Place:
Correct Answer:
Box 1: Facial recognition -

Face detection that perceives faces and attributes in an image; person identification that matches an individual in your private repository of up
to 1 million people; perceived emotion recognition that detects a range of facial expressions like happiness, contempt, neutrality, and fear; and
recognition and grouping of similar faces in images.
Box 2: OCR -
Box 3: Objection detection -

Object detection is similar to tagging, but the API returns the bounding box coordinates (in pixels) for each object found. For example, if an
image contains a dog, cat and person, the Detect operation will list those objects together with their coordinates in the image. You can use this
functionality to process the relationships between the objects in an image. It also lets you determine whether there are multiple instances of
the same tag in an image.
The Detect API applies tags based on the objects or living things identified in the image. There is currently no formal relationship between the
tagging taxonomy and the object detection taxonomy. At a conceptual level, the Detect API only finds objects and living things, while the Tag
API can also include contextual terms like "indoor", which can't be localized with bounding boxes.
Reference:
https://azure.microsoft.com/en-us/services/cognitive-services/face/ https://docs.microsoft.com/en-us/azure/cognitive-services/computer-
vision/concept-object-detection
  Vanshhh123 1 day, 21 hours ago

correct answer
upvoted 1 times

answer is correct
upvoted 2 times
You need to determine the location of cars in an image so that you can estimate the distance between the cars.
Which type of computer vision should you use?
A. optical character recognition (OCR)
B. object detection
C. image classification
D. face detection
Correct Answer: B
Reference:
  Omas 3 weeks, 1 day ago

upvoted 1 times

ans is correct
upvoted 3 times

correct answer
upvoted 2 times

ans is correct
upvoted 4 times
HOTSPOT -
Hot Area:
Correct Answer:
Azure Custom Vision is a cognitive service that lets you build, deploy, and improve your own image classifiers. An image classifier is an AI
service that applies labels (which represent classes) to images, according to their visual characteristics. Unlike the Computer Vision service,
Custom Vision allows you to specify the labels to apply.
Note: The Custom Vision service uses a machine learning algorithm to apply labels to images. You, the developer, must submit groups of
images that feature and lack the characteristics in question. You label the images yourself at the time of submission. Then the algorithm trains
to this data and calculates its own accuracy by testing itself on those same images. Once the algorithm is trained, you can test, retrain, and
eventually use it to classify new images according to the needs of your app. You can also export the model itself for offline use.
Incorrect Answers:
Computer Vision:
Azure's Computer Vision service provides developers with access to advanced algorithms that process images and return information based on
the visual features you're interested in. For example, Computer Vision can determine whether an image contains adult content, find specific
brands or objects, or find human faces.
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/home
  Katiel Highly Voted  7 months, 3 weeks ago

Custom vision is correct
https://docs.microsoft.com/en-gb/learn/modules/detect-objects-images-custom-vision/2-object-detection-azure
upvoted 20 times

Custom Vision is correct since we are using our own images.
upvoted 7 times
  leecirca05 Most Recent  1 month, 3 weeks ago

correct
upvoted 1 times
  Happiness20 2 months, 3 weeks ago

The answer is Custom Vision
upvoted 1 times

The answer is definitely Custom Vision.
upvoted 1 times

Ansewer is correct.
upvoted 1 times
  vhx 7 months, 3 weeks ago

I guess computer vision should be the answer
upvoted 3 times

Custom vision is correct.
The Computer Vision cognitive service provides a pre-trained computer vision model that you can use to analyze images.
The Custom Vision cognitive services enables you to train a custom model for either image classification or object detection.
upvoted 19 times
You send an image to a Computer Vision API and receive back the annotated image shown in the exhibit.
Which type of computer vision was used?
A. object detection
B. semantic segmentation
C. optical character recognition (OCR)
D. image classification
Correct Answer: A
Reference:

ans is correct
upvoted 14 times
  gills Highly Voted  2 months ago

Image classification involves predicting the class of one object in an image. Object localization refers to identifying the location of one or more
objects in an image and drawing abounding box around their extent. Object detection combines these two tasks and localizes and classifies one or
more objects in an image.
When a user or practitioner refers to “object recognition“, they often mean “object detection“. So clearly the answer for this question is object
detection.
upvoted 5 times
  poo12 Most Recent  1 week ago

ans is correct
upvoted 1 times
  Tas006 1 month, 2 weeks ago

Can we confirm here that answer is A ?
upvoted 2 times
  Nitin2 2 months, 1 week ago

A is correct. Image classification means classifying the entire image into a category. Object detection is detecting different objects within an image.
Image classification here would be saying overall image is Fruits.
upvoted 3 times
  DWDG 2 months, 2 weeks ago

A for me
upvoted 1 times
  Parzival 2 months, 3 weeks ago

Classification will say those are fruits, but Object detection gives labels based of the objects in the image. A simple normal way to understand it.
upvoted 1 times
  Happiness20 2 months, 3 weeks ago

Object Detection is the answer
upvoted 1 times
  Jay_KOR 3 months ago

Answer is A.
https://docs.microsoft.com/en-ca/learn/modules/get-started-ai-fundamentals/4-understand-computer-vision
upvoted 2 times
  dee_dee 3 months ago

Pls I need to know the difference between image classification and object recognition
upvoted 1 times

Answer is D. image classification
upvoted 1 times

upvoted 1 times
  Abhitera 4 months, 1 week ago

Only object detection gives probability score so ans is correct
upvoted 3 times
  zic04 4 months, 1 week ago

D for me
upvoted 1 times
  Jned 4 months, 2 weeks ago

It's D :
As with any form of classification, creating an image classification solution involves training a model using a set of existing data for which the class
is already known. In this case, the existing data consists of a set of categorized images, which you must upload to the Custom Vision service and
tag with appropriate class labels. After training the model, you can publish it as a service for applications to use.
upvoted 2 times
What are two tasks that can be performed by using the Computer Vision service? Each correct answer presents a complete solution.
A. Train a custom image classification model.
B. Detect faces in an image.
C. Recognize handwritten text.
D. Translate the text in an image between languages.
Correct Answer: BC
B: Azure's Computer Vision service provides developers with access to advanced algorithms that process images and return information based
on the visual features you're interested in. For example, Computer Vision can determine whether an image contains adult content, find specific
brands or objects, or find human faces.
C: Computer Vision includes Optical Character Recognition (OCR) capabilities. You can use the new Read API to extract printed and handwritten
text from images and documents.
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/home

BC is correct
upvoted 33 times

BC correct as given.
---------------
Microsoft Azure provides multiple cognitive services that you can use to detect and analyze faces, including:
**Computer Vision, which offers face detection and some basic face analysis, such as determining age.
**Video Indexer, which you can use to detect and identify faces in a video.
**Face, which offers pre-built algorithms that can detect, recognize, and analyze faces.
Of these, Face offers the widest range of facial analysis capabilities, so we'll focus on that service in this module.
------------------
The ability to extract text from images is handled by the Computer Vision service, which also provides image analysis capabilities.
The Computer Vision service provides two application programming interfaces (APIs) that you can use to read text in images: the OCR API and the
Read API.
upvoted 13 times
  O_Anjum Most Recent  3 weeks, 2 days ago

A. Custom vision
B. Face Analysis
C. OCR/Read API
D. NLP
First, three fall into Vision, but B and C specifically fall into Computer Vision. So, correct answer.
upvoted 1 times
  tjli 2 months ago

in exam 12 apr 2021, BC should be right
upvoted 4 times
  SamSwift 3 months ago

answers are correct
upvoted 2 times

upvoted 3 times

A. Train a custom image classification model. --> Custom Vision
B. Detect faces in an image. --> Computer Vision. (Face)
C. Recognize handwritten text. --> Computer Vision. (OCR)
D. Translate the text in an image between languages. - Not a vision service.
upvoted 13 times
  Raja3sa 6 months, 1 week ago

BC are correct
upvoted 4 times
  Rahulm025 8 months, 1 week ago

Option A cannot be included as it is mentioned 'Custom Images'. We custom vision for custom images
upvoted 12 times
  shanks167 8 months, 1 week ago

I think the answer should be A & B
upvoted 6 times
  rhr 3 months, 1 week ago

No A doesn't fall under computer vision it's part of the custom vision. B and C are correct
upvoted 8 times
  danflr 5 months, 1 week ago

A is wrong because you can not train the computer vision with custom images. This would be custom vision.
upvoted 12 times
What is a use case for classification?
A. predicting how many cups of coffee a person will drink based on how many hours the person slept the previous night.
B. analyzing the contents of images and grouping images that have similar colors
C. predicting whether someone uses a bicycle to travel to work based on the distance from home to work
D. predicting how many minutes it will take someone to run a race based on past race times
Correct Answer: C
Incorrect Answers:
A: This is Regression.
B: This is Clustering.
D: This is Regression.
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/algorithm-module-reference/linear-regression https://docs.microsoft.com/en-
us/azure/machine-learning/studio-module-reference/machine-learning-initialize-model-clustering

this sis wrong again. Grouping of objects with similar colors is clustering and not classification. Classification is point 3 where we will predict
whether the person will go to office by cycle (answer - yes or no - hence clasification) depending on the distance
upvoted 59 times

Incorrect answer, correct answer is C.
A refers to regression.
B refers to Clustering
C refers to Classification
D refers to Regression
upvoted 43 times

C is correct, Classification.
upvoted 1 times

regression, clustering, classification, regression.
upvoted 1 times

B is Clustering, C is the right answer
upvoted 1 times

All the answers except option B seems to be examples of classification.
upvoted 1 times
  sabderushikesh 4 weeks, 1 day ago

answer should be C
upvoted 2 times

1. Regression
2. Clustering
3. Classification
4. Regression
upvoted 1 times
  BankZenith 1 month ago

Classification is right answer.
upvoted 2 times
  Janu12 2 months ago

C is correct
upvoted 2 times

I believe C is correct
upvoted 2 times
  Dr3w666 2 months, 3 weeks ago

I would never pay for examtopics contents... It's so unreliable. Only the comments make it worthwhile.
upvoted 7 times
  allanm 1 month, 1 week ago

That is a very stupid thing to say. The provided answers may be wrong most of the time but the real value of these questions come from the
community discussion of said questions. It not only gives the individual a flavour for the questions that will appear in the real exam but also
significantly increases the score for an individual. Having said that, I'd personally only pay if I'm not confident with the exam topic or If it is an
associate/expert certification. Fundamentals should be fine to use the free version.
upvoted 2 times
  Adedoyin_Simeon 2 months, 1 week ago

You shouldn't say so. Without the examtopics, the comments won't exist. It is the fact that we are seeing the questions that made us know
certain answers are correct or wrong. Examtopics atleast provides us an idea of how the questions are set. That to me is big enough and
worthwhile. Moreover, there are more correct answers than the wrong ones.
upvoted 28 times

answer should be C
upvoted 1 times

The answer is C
upvoted 1 times
  Pwndps 4 months, 2 weeks ago

C should be correct ans
upvoted 1 times
  mimi 4 months, 3 weeks ago

correct answer is C. B for clustering
upvoted 1 times
  Princy 4 months, 3 weeks ago

Answer should be C. Grouping of object based on similarities is clustering not classification.
upvoted 1 times
What are two tasks that can be performed by using computer vision? Each correct answer presents a complete solution.
A. Predict stock prices.
B. Detect brands in an image.
C. Detect the color scheme in an image
D. Translate text between languages.
E. Extract key phrases.
Correct Answer: BC
B: Identify commercial brands in images or videos from a database of thousands of global logos. You can use this feature, for example, to
discover which brands are most popular on social media or most prevalent in media product placement.
C: Analyze color usage within an image. Computer Vision can determine whether an image is black & white or color and, for color images,
identify the dominant and accent colors.
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/overview

B&C are correct answers
upvoted 67 times
  wreck Highly Voted  8 months, 2 weeks ago

Detech Color scheme and Brand images are correct based on
Detect the color scheme

Analyze color usage within an image. Computer Vision can determine whether an image is black & white or color and, for color images, identify the
dominant and accent colors. Detect the color scheme
and
Azure's Computer Vision service gives you access to advanced algorithms that process images and return information based on the visual features
you're interested in. For example, Computer Vision can determine whether an image contains adult content, find specific brands or objects, or find
human faces.
upvoted 19 times

B&C are correct.
upvoted 1 times

Extracting key phrases, is not a computer vision, it is a part of NLP. B and C are the right answers
upvoted 2 times

BC are the correct options
upvoted 1 times
  Ajao 3 weeks, 2 days ago

The correct answer is B&C. E is for text analytics. Note the difference between "extract printed & handwritten text" and "extract key phrases"
upvoted 1 times

B & C are correct,E was only going to be an answer if the key phrases were extracted from an image,in that case it then fall under computer vision
but its generically stated like that then its part of NLP not computer vision
upvoted 1 times

BC are correct!
upvoted 3 times

A. Predict stock prices. (ML Regression)
B. Detect brands in an image. (Computer Vision)
C. Detect the color scheme in an image (Computer Vision)
D. Translate text between languages. (PNL, Translator Text)
E. Extract key phrases. (AI Workload Computer Vision, as Azure service is Form
Recognizer)
upvoted 4 times

Answer is B&C, it's refering to task
upvoted 2 times
  rachhek 1 month, 2 weeks ago

I think this website marks the wrong answer on purpose to encourage discussions XD
upvoted 4 times
  AAwaad 2 months ago

BCE are all correct as per the documentation, be careful!
B and C:
https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/overview-image-analysis
E:
https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/overview-ocr
upvoted 1 times
  dduque10 1 month, 3 weeks ago

E is from Text Analytics, not Computer Vision
upvoted 3 times

BC is okay
upvoted 1 times
  tjli 2 months ago

Answer should be B&C, in exam 12 apr 2021
upvoted 2 times
  Souravg94 2 months, 1 week ago

B & C are correct.
Extracting key phases is related to OCR
upvoted 1 times
  Deadshot3nod3 2 months, 1 week ago

B C and E all three are correct because we know we can use computer vision for image analysis, but E is also correct because we can do key value
extraction frim form analysis service in azure which can be enabled y computer vision
upvoted 2 times
  ceasar3000 2 months, 2 weeks ago

Man this guy giving answers hasn't learnt Microsoft docs on AI. The answer is BC
upvoted 2 times
  Kishorepi 2 months, 2 weeks ago

Key Phrase extraction is done by NLP. I think B & C are correct.
upvoted 2 times
Your company wants to build a recycling machine for bottles. The recycling machine must automatically identify bottles of the correct shape and
reject all other items.
Which type of AI workload should the company use?
A. anomaly detection
B. conversational AI
C. computer vision
D. natural language processing
Correct Answer: C
Azure's Computer Vision service gives you access to advanced algorithms that process images and return information based on the visual
features you're interested in. For example, Computer Vision can determine whether an image contains adult content, find specific brands or
objects, or find human faces.
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/overview
  fatrapb1t Highly Voted  6 months, 3 weeks ago

C is correct. Anomaly detection is unsupervised learning that detect "deviation" from norm. To correctly identify the "correct" plastic bottle,
computer vision should be used.
upvoted 24 times
  ZVV 1 month, 3 weeks ago

You have computer vision model for any bottle size you need?
I don't think so.
upvoted 1 times
  GraceCyborg Highly Voted  7 months, 3 weeks ago

answer is correct
upvoted 10 times
  Sudesh Most Recent  1 month, 2 weeks ago

C is correct
upvoted 1 times
  kogw344pre 2 months ago

computer vision is correct
upvoted 2 times
  ticbab 2 months ago

Maybe you need at least Custom vision + Anomaly. Deviations of the size is anomaly thus Anomaly detection, but you need Vision for input
perhaps?
upvoted 4 times

C. Computer Vision is the best answer here, but it should be Custom Vision.
The documentation of Anomaly Detection never mentions images or vision, only time-series data as input.
https://docs.microsoft.com/en-au/azure/cognitive-services/anomaly-detector/overview
Maybe, at the actual exam, the option is Custom Vision instead of Computer Vision. Can someone confirm or deny this assumption?
upvoted 1 times

The key here is "shape" not "sizes". Agree with the comments on custom vision, however since it is not listed among the options, the correct
answer is computer vision. Granted at first glance, it is tempting to select anomaly detection and it is understandable.
upvoted 1 times
  Sonuand 3 months, 1 week ago

It is NOT Computer Vision, if we are taking about "Shape Detection", it must be "Custom Vision", not computer vision. Because Computer Vision
can detect simple shapes, not shapes of bottles (coke bottle, water bottle, medicine bottle. etc). But "Custom Vision" is not shown as an option,
hence the closest is "Anomaly Detection"
upvoted 2 times

You are right that the best options is Custom Vision is not in the options. The nearest is Computer Vision, anomaly detection has no sense at all
with this question.
upvoted 2 times

Addictionaly they ask for "type of AI workload" not Which Azure Service, so Computer Vision is correct
upvoted 1 times

Anomaly detection is the identification of rare items, events or observations which raise suspicions by differing significantly from the majority of
the data. Nothing in the question indicate anomaly detection so it is NOT anomaly detection.
upvoted 2 times

It's computer vision
upvoted 1 times
  Atul301994 3 months, 1 week ago

Anamoly detection
upvoted 1 times
  AIexpertpinky 5 months, 1 week ago

https://docs.microsoft.com/en-us/azure/machine-learning/algorithm-module-reference/pca-based-anomaly-detection
Clear case of anomaly

upvoted 2 times
  bijs 5 months, 3 weeks ago

Anomaly is to find unusual pattern. Here the sample set can contain all types of bottle and the problem to identofy the correct dimension. There is
nothing unsual about it. So it should be computer vision and the answer is correct, IMO
upvoted 3 times

Should be Classification
upvoted 1 times

Anomaly Detection is the right answer.
Practically, it is not possible to train the model on invalid / incorrect sizes. Therefore, to create an anomaly detection model, you prepare training
data with all the valid sizes of bottles. If something doesn't fall under the valid ones, will be rejected.
This scenario is similar to detecting fraudulent transactions, you often don't have enough examples of fraud to train on. But you might have many
examples of good transactions. The PCA-Based Anomaly Detection module solves the problem by analyzing available features to determine what
constitutes a "normal" class. The module then applies distance metrics to identify cases that represent anomalies. This approach lets you train a
model by using existing imbalanced data.
upvoted 2 times
  Adedoyin_Simeon 2 months, 1 week ago

I will like to call your attention to the fact that this involves images, a vision project.
upvoted 1 times

No need to use anomaly detection module to analyze available features. Only need to identify the correct bottle shape
upvoted 3 times
  Dotzs 3 months, 1 week ago

You are right
upvoted 1 times
  Geekie 7 months ago

Answer is Anomaly detection.
upvoted 2 times

Answer should be A-Anomaly Detection
https://docs.microsoft.com/en-in/learn/modules/get-started-ai-fundamentals/3-understand-anomaly-detection
Imagine you're creating a software system to monitor credit card transactions and detect unusual usage patterns that might indicate fraud.
Or an application that tracks activity in an automated production line and identifies failures. <<<<<<<<<<
Or a racing car telemetry system that uses sensors to proactively warn engineers about potential mechanical failures before they happen.
upvoted 7 times

Anomaly detection might indicate fraud but is not used to identify the correct bottle shape.
upvoted 10 times
  ealcober 7 months, 3 weeks ago

the question asks fot WORKLOAD (anomaly detect.) not SERVICE (Computer Vision...)
upvoted 3 times

computer vision is a workload
upvoted 3 times
HOTSPOT -
Hot Area:
Correct Answer:
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/get-started-build-detector
  mnmcbl 2 days, 18 hours ago

For Q1, Object Deteciton has no further types to choose from.
Classification has 2 classification types to choose - MultiClass & MultiLabel.
[Object Detection] https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/get-started-build-detector
[Classification] https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/getting-started-build-a-classifier
upvoted 2 times
In which two scenarios can you use the Form Recognizer service? Each correct answer presents a complete solution.
A. Extract the invoice number from an invoice.
B. Translate a form from French to English.
C. Find image of product in a catalog.
D. Identify the retailer from a receipt.
Correct Answer: AD
Reference:
https://azure.microsoft.com/en-gb/services/cognitive-services/form-recognizer/#features

answer is ok
upvoted 9 times
  mikech Most Recent  2 weeks, 2 days ago

answer is correct
upvoted 1 times
  Ifexalex 2 months, 1 week ago

A and D correct
upvoted 1 times
  Bjlaxy1 2 months, 1 week ago

I think option D should be identify, not identity.
upvoted 1 times
  Jenny1 3 months ago

Correct
upvoted 1 times

answer is correct
upvoted 1 times
HOTSPOT -
You have a database that contains a list of employees and their photos.
You are tagging new photos of the employees.
For each of the following statements select Yes if the statement is true. Otherwise, select No.
Hot Area:
Correct Answer:
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/face/overview https://docs.microsoft.com/en-us/azure/cognitive-
services/face/concepts/face-detection
  SnowCheetah 6 days, 22 hours ago

It's a bit tricky on the last statement. When member wear glasses, it might cause on face detection tell error. BUT NOT ALWAYS. Thus I think it's
correct answer Y/Y/N
upvoted 1 times
You need to develop a mobile app for employees to scan and store their expenses while travelling.
Which type of computer vision should you use?
A. semantic segmentation
B. image classification
C. object detection
D. optical character recognition (OCR)
Correct Answer: D
Azure's Computer Vision API includes Optical Character Recognition (OCR) capabilities that extract printed or handwritten text from images.
You can extract text from images, such as photos of license plates or containers with serial numbers, as well as from documents - invoices,
bills, financial reports, articles, and more.
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/concept-recognizing-text
  danflr Highly Voted  5 months, 1 week ago

They should add "Form Recognizer" as option as this is perfect for receipt reading: https://azure.microsoft.com/en-us/services/cognitive-
services/form-recognizer/
upvoted 10 times
  PM2 Highly Voted  7 months, 1 week ago

Correct Answer
upvoted 9 times
  Kanjati Most Recent  1 month ago

OCR does text extraction as well!
upvoted 2 times

upvoted 1 times
  MLMK 6 months, 3 weeks ago

Answer is correct
upvoted 3 times
HOTSPOT -
Hot Area:
Correct Answer:
Reference:

Classify Email messages is correct answer
upvoted 20 times
  SnowCheetah Most Recent  6 days, 22 hours ago

Classify Email which mean it need read through email content == which involve NLP
Answer A is correct
upvoted 1 times

Answer is correct
upvoted 1 times

upvoted 1 times

Answer is classify email messages
upvoted 1 times

upvoted 2 times

upvoted 2 times
  shanks167 8 months, 1 week ago

stop a process in a factory when extremely high temperatures are registered. -anomaly detection and NLP
upvoted 1 times
  Rahulm025 8 months, 1 week ago

It cannot be NLP because temperatures are values not text data.
upvoted 11 times
Which AI service can you use to interpret the meaning of a user input such as ‫ג‬€Call me back later?‫ג‬€
A. Translator Text
B. Text Analytics
C. Speech
D. Language Understanding (LUIS)
Correct Answer: D
Language Understanding (LUIS) is a cloud-based AI service, that applies custom machine-learning intelligence to a user's conversational,
natural language text to predict overall meaning, and pull out relevant, detailed information.
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/what-is-luis
You are developing a chatbot solution in Azure.

Which service should you use to determine a user‫ג‬€™s intent?
A. Translator Text
B. QnA Maker
C. Speech
Correct Answer: D
Language Understanding (LUIS) is a cloud-based API service that applies custom machine-learning intelligence to a user's conversational,
natural language text to predict overall meaning, and pull out relevant, detailed information.
Design your LUIS model with categories of user intentions called intents. Each intent needs examples of user utterances. Each utterance can
provide data that needs to be extracted with machine-learning entities.
Reference:
  bapu2020 6 days, 17 hours ago

D is correct.
Explanation/Reference:
Language Understanding (LUIS) is a cloud-based API service that applies custom machine-learning intelligence to a user’s conversational, natural
language text to predict overall meaning, and pull out relevant, detailed information.
Design your LUIS model with categories of user intentions called intents. Each intent needs examples of user utterances. Each utterance can
provide data that needs to be extracted with machine-learning entities.
Reference:
upvoted 2 times
  naadherah 1 week, 2 days ago

I think its B
upvoted 2 times
  AZ900test 3 days, 5 hours ago

I think it's B as well.
upvoted 1 times
You need to make the press releases of your company available in a range of languages.
Which service should you use?
A. Translator Text
B. Text Analytics
C. Speech
Correct Answer: A
Translator is a cloud-based machine translation service you can use to translate text in near real-time through a simple REST API call. The
service uses modern neural machine translation technology and offers statistical machine translation technology. Custom Translator is an
extension of Translator, which allows you to build neural translation systems.
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/translator/
  Mitesh3 Highly Voted  5 months, 3 weeks ago

Speech service should be the answer as press release has live audio which needs to be converted into other languages.
upvoted 6 times
  aaronlcs 2 months, 2 weeks ago

Translator Text should be the answer.
Press release is a written communication. Speech wouldn't make sense. Plus, the Speech service doesn't translate languages, it "translates" audio
into text, and vice versa.
upvoted 5 times
  Ajao Most Recent  3 weeks, 2 days ago

The answer is A. Press release is text base while Press briefing is audio base
upvoted 1 times
  aras 3 months, 3 weeks ago

Translator Text is correct.
A press release is a written communication that reports specific but brief information about an event, circumstance, product launch, or other
happening.
upvoted 4 times

Translator Text is the correct answer.
Microsoft Azure provides cognitive services that support translation. Specifically, you can use the following services:
The Translator Text service, which supports text-to-text translation.
The Speech service, which enables speech-to-text and speech-to-speech translation.
https://docs.microsoft.com/en-us/learn/modules/translate-text-with-translation-service/2-get-started-azure
upvoted 3 times
HOTSPOT -
Hot Area:
Correct Answer:
The Text Analytics API is a cloud-based service that provides advanced natural language processing over raw text, and includes four main
functions: sentiment analysis, key phrase extraction, named entity recognition, and language detection.
Box 1: Yes -
You can detect which language the input text is written in and report a single language code for every document submitted on the request in a
wide range of languages, variants, dialects, and some regional/cultural languages. The language code is paired with a score indicating the
strength of the score.
Box 2: No -
Box 3: Yes -
Named Entity Recognition: Identify and categorize entities in your text as people, places, organizations, date/time, quantities, percentages,
currencies, and more.
Well-known entities are also recognized and linked to more information on the web.
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/overview
  ramjisriram Highly Voted  4 months, 1 week ago

Given answers are correct. Ink service identifies handwritten.
upvoted 6 times
  Jenny1 Most Recent  3 months ago

Correct
upvoted 4 times
  DarthVader123 5 months, 4 weeks ago

Correct
upvoted 1 times
DRAG DROP -
Match the types of natural languages processing workloads to the appropriate scenarios.
Select and Place:
Correct Answer:
Box 1: Entity recognition -

Named Entity Recognition (NER) is the ability to identify different entities in text and categorize them into pre-defined classes or types such as:
person, location, event, product, and organization.
Box 2: Sentiment analysis -

Sentiment Analysis is the process of determining whether a piece of writing is positive, negative or neutral.
Box 3: Translation -
Using Microsoft‫ג‬€™s Translator text API
This versatile API from Microsoft can be used for the following:
Translate text from one language to another.
Transliterate text from one script to another.
Detecting language of the input text.
Find alternate translations to specific text.
Determine the sentence length.
Reference:
https://docs.microsoft.com/en-in/azure/cognitive-services/text-analytics/how-tos/text-analytics-how-to-entity-linking?tabs=version-3-preview
https://azure.microsoft.com/en-us/services/cognitive-services/text-analytics
  Mccumhal Highly Voted  8 months, 1 week ago

Box 1 is entity recognition.
Classify a broad range of entities in text, such as people, places, organisations, date/time and percentages, using named entity recognition.
Whereas:- Get a list of relevant phrases that best describe the subject of each record using key phrase extraction.
upvoted 48 times

Box 1 --> Entity recognition
Box 2 --> Sentiment analysis
Box 3 --> Translation
upvoted 21 times

the first box in entity recognition seee documentation below
https://monkeylearn.com/blog/named-entity-recognition/
upvoted 1 times

No a Key phrase :"This capability is useful if you need to quickly identify the main points in a collection of documents. For example, given input text
"The food was delicious and there were wonderful staff", the service returns the main talking points: "food" and "wonderful staff".
https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/how-tos/text-analytics-how-to-keyword-extraction
upvoted 2 times
  afzal95 2 months, 1 week ago

since it says broad extraction of entities, i think key phrase is correct
upvoted 1 times

Answer is 1.Entity recognition, 2.Sentiment analysis and 3.Translation
upvoted 3 times

Box 1 should be entity recognition
upvoted 1 times

Answer should be Entity recognition, Sentiment analysis, Translation
upvoted 1 times
  Rorschach666 4 months, 1 week ago

Box 1 is Named entity recognition
Named Entity Recognition (NER) can Identify and categorize entities in your text as people, places, organizations, quantities, Well-known entities
are also recognized and linked to more information on the web.
Key phrase extraction

Use key phrase extraction to quickly identify the main concepts in text. For example, in the text "The food was delicious and there were wonderful
staff", Key Phrase Extraction will return the main talking points: "food" and "wonderful staff".
upvoted 1 times
  SK27 7 months, 1 week ago

1 should be entity recognition
upvoted 2 times
  ealcober 7 months, 3 weeks ago

On their own explanation they mention entity recognition. Ther's some error here with first that oviously is that answer.
upvoted 3 times
  AshML 7 months, 3 weeks ago

The answer for 1st is actually "Named Entity Recognition" but they called it Entity Recognition. "Named Entity Recognition (NER)
person, location, event, product and organization." https://docs.microsoft.com/en-in/azure/cognitive-services/text-analytics/how-tos/text-
analytics-how-to-entity-linking?tabs=version-3-preview
upvoted 4 times
  vedrurekko 8 months ago

I also believe that the box 1 is entity recognition.
upvoted 5 times
HOTSPOT -
Hot Area:
Correct Answer:
Box 1: Yes -
Content Moderator is part of Microsoft Cognitive Services allowing businesses to use machine assisted moderation of text, images, and videos
that augment human review.
The text moderation capability now includes a new machine-learning based text classification feature which uses a trained model to identify
possible abusive, derogatory or discriminatory language such as slang, abbreviated words, offensive, and intentionally misspelled words for
review.
Box 2: No -
Azure's Computer Vision service gives you access to advanced algorithms that process images and return information based on the visual
features you're interested in. For example, Computer Vision can determine whether an image contains adult content, find specific brands or
objects, or find human faces.
Box 3: Yes -
Reference:
https://azure.microsoft.com/es-es/blog/machine-assisted-text-classification-on-content-moderator-public-preview/

upvoted 12 times
  Tas006 Most Recent  1 month, 1 week ago

Answer here is N,N,Y
upvoted 1 times

I think you are wrong! You need Text moderation "Scans text for offensive content, sexually explicit or suggestive content, profanity, and personal
data." https://docs.microsoft.com/en-us/azure/cognitive-services/content-moderator/overview
upvoted 2 times
  Edwardenis 1 month, 3 weeks ago

I Think the same
upvoted 1 times
  TheB 2 months, 2 weeks ago

correct
upvoted 1 times
  Pranav_K 5 months, 3 weeks ago

Profanitic was key word :).. answer is correct
upvoted 2 times
You are developing a natural language processing solution in Azure. The solution will analyze customer reviews and determine how positive or
negative each review is.
This is an example of which type of natural language processing workload?
A. language detection
B. sentiment analysis
C. key phrase extraction
D. entity recognition
Correct Answer: B
Reference:

correct
upvoted 2 times

Answer is correct
upvoted 1 times

upvoted 2 times

ans is correct
upvoted 3 times
You use natural language processing to process text from a Microsoft news story.
You receive the output shown in the following exhibit.
Which type of natural languages processing was performed?
A. entity recognition
B. key phrase extraction
C. sentiment analysis
D. translation
Correct Answer: A
person, location, event, product, and organization.
In this question, the square brackets indicate the entities such as DateTime, PersonType, Skill.
Reference:
https://docs.microsoft.com/en-in/azure/cognitive-services/text-analytics/how-tos/text-analytics-how-to-entity-linking?tabs=version-3-preview
  test32566 Highly Voted  8 months, 1 week ago

This is entity recognition
upvoted 58 times
  kty 2 months, 3 weeks ago

I agree
Extract a broad range of pre-built entities such as people, places, organizations, date/time, numerals and over 100 types of personally
identifiable information (PII), including protected health information (PHI), in documents using named entity recognition.
Quickly evaluate and identify the main points in unstructured text. Get a list of relevant phrases that best describe the subject of each record
using key phrase extraction. Easily organize information to make sense of important topics and trends.
upvoted 2 times
  digitallycan Highly Voted  7 months ago

Entity recognition has category classification, key phrase extraction does not. Take a look at Key Phrase extraction results:
[https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/how-tos/text-analytics-how-to-keyword-extraction] with NER results:
[https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/how-tos/text-analytics-how-to-entity-linking?tabs=version-3-preview]
upvoted 10 times

The correct answer is Name Entity Recognition
upvoted 1 times

The output are not phrases, rather entities. So it's A
upvoted 1 times
  Jovanny 2 months, 1 week ago

At first, I thought 💭 it's key phrase extraction but now I believe it's entity recognition.
upvoted 2 times

A. Entity recognition
In the link provided for the answer you can see the following example:
NAMED ENTITIES: Contoso [Organization]
Steakhouse [Location]
NYC [Location-GPE]
last week [DateTime-DateRange]
dinner party [Event]
chief cook [PersonType]
owner [PersonType]
John Doe [Person]
kitchen [Location-Structural]
Sirloin steak [Product]
www.contososteakhouse.com [URL]
312-555-0176 [Phone Number]
email [Skill]
order@contososteakhouse.com [Email]
contososteakhouse [Organization]
So correct link but wrong answer :)

upvoted 2 times

Answer is A. entity recognition
upvoted 1 times

It is Entity recognition
upvoted 1 times
  WissoYassin 3 months, 1 week ago

entity recognition is the correct answer.
upvoted 1 times
  Vkp 3 months, 2 weeks ago

Entity recognition is the correct answer.
Watch the below video
upvoted 1 times

Answer should be entity recognition
upvoted 1 times
  CarolM 3 months, 3 weeks ago

Key Phrase extraction
upvoted 2 times

The answer is A, named Entity
upvoted 1 times

Correct answer is entity recognition.
upvoted 1 times
  Whirly 5 months ago

It is Entity Recognition
https://azure.microsoft.com/en-us/services/cognitive-services/text-analytics/#features
NAMED ENTITIES: Contoso Steakhouse [Location]

midtown NYC [Location]
last week [DateTime-DateRange]
chief cook [PersonType]
owner [PersonType]
John Doe [Person]
kitchen [Location-Structural]
www.contososteakhouse.com [URL]
312-555-0176 [Phone Number]
email [Skill]
order@contososteakhouse.com [Email]
upvoted 2 times
  AIexpertpinky 5 months ago

It is Entity Recognition
upvoted 1 times

it is entity recognition because it provides the type of each entity while Key phrase extraction doesn't
upvoted 2 times
DRAG DROP -
You plan to apply Text Analytics API features to a technical support ticketing system.
Match the Text Analytics API features to the appropriate natural language processing scenarios.
To answer, drag the appropriate feature from the column on the left to its scenario on the right. Each feature may be used once, more than once, or
not at all.
Select and Place:
Correct Answer:
Box1: Sentiment analysis -

Box 2: Broad entity extraction -

Broad entity extraction: Identify important concepts in text, including key
Key phrase extraction/ Broad entity extraction: Identify important concepts in text, including key phrases and named entities such as people,
places, and organizations.
Box 3: Entity Recognition -

Named Entity Recognition: Identify and categorize entities in your text as people, places, organizations, date/time, quantities, percentages,
currencies, and more.
Well-known entities are also recognized and linked to more information on the web.
Reference:
https://azure.microsoft.com/en-us/services/cognitive-services/text-analytics

it is correct
upvoted 16 times
  sidbarker Most Recent  2 months, 1 week ago

It's correct!
upvoted 2 times

answers are correct
upvoted 1 times

Answer is correct
upvoted 1 times
  robyteja 4 months ago

Not language detection
upvoted 1 times

Answer is correct.
upvoted 1 times

upvoted 1 times
  SMatishMe 6 months, 1 week ago

Answer is definitely correct. Check the answer of previous question where there has been healthy debate, it contradicts with the answer of this re
key phrase detection
upvoted 3 times

upvoted 1 times
  digitallycan 7 months ago

Answer is correct.
upvoted 4 times
  PremT 8 months, 2 weeks ago

Box 2 and 3 seems exchanged ?
upvoted 4 times

i think you are right
upvoted 1 times
  jackreacher 8 months, 1 week ago

No it seems correct
upvoted 14 times
  adelino13 6 months ago

Message For all person,,please, if you are not sure of your answer in this examtopic, please do not write anything here, because we do not
need your opinion but we need the correct answer.. thanks for your understanding -------------------------------------
upvoted 32 times
You are developing a solution that uses the Text Analytics service.
You need to identify the main talking points in a collection of documents.
Which type of natural language processing should you use?
A. entity recognition
C. sentiment analysis
D. language detection
Correct Answer: B
Broad entity extraction: Identify important concepts in text, including key
Key phrase extraction/ Broad entity extraction: Identify important concepts in text, including key phrases and named entities such as people,
places, and organizations.
Reference:

The answer is key phrase extraction. The emphasis should be "main talking points"
upvoted 3 times
  sidbarker 2 months, 1 week ago

It's correct:
upvoted 1 times

The answer given is correct, the key to understanding key phrase extraction is looking for "key" (for lack of a better word) words like "main",
"important", "summary", even "broad" etc..as per previous questions.
upvoted 4 times
  anki09 3 months, 2 weeks ago

B (KP) is right
upvoted 1 times

Use key phrase extraction to quickly identify the main concepts in text. For example, in the text "The food was delicious and there were wonderful
staff", Key Phrase Extraction will return the main talking points: "food" and "wonderful staff".
upvoted 2 times

ans is correct
upvoted 2 times
In which two scenarios can you use speech recognition? Each correct answer presents a complete solution.
A. an in-car system that reads text messages aloud
B. providing closed captions for recorded or live videos
C. creating an automated public address system for a train station
D. creating a transcript of a telephone call or meeting
Correct Answer: BD
Reference:
https://azure.microsoft.com/en-gb/services/cognitive-services/speech-to-text/#features
  vietit 1 month, 1 week ago

I think this question should be put more clear that it is Speech to Text recognition.
upvoted 1 times
  nerv 1 month, 1 week ago

Speech recognition cannot be anything else in Azure AI but Speech to text recognition. So , this "to text" is in fact unnecessary.
upvoted 3 times
  BigJose 3 months, 1 week ago

Answer is correct. A is Speech Synthesis, not Speech Recognition
upvoted 3 times

Or as better known in Azure - Text-to-Speech.
upvoted 1 times
  Yass92 3 months, 3 weeks ago

if you see next question, A should be speech as well?!
upvoted 4 times

ans is correct
upvoted 4 times
HOTSPOT -
Hot Area:
Correct Answer:
Reference:
https://azure.microsoft.com/en-gb/services/cognitive-services/speech-to-text/#features
You need to build an app that will read recipe instructions aloud to support users who have reduced vision.
Which version service should you use?
A. Text Analytics
B. Translator Text
C. Speech
Correct Answer: C
Reference:
https://azure.microsoft.com/en-us/services/cognitive-services/text-to-speech/#features
  TheB 2 months, 2 weeks ago

Answer C is correct.
upvoted 3 times

answer is correct
upvoted 1 times

ans is correct
upvoted 4 times
HOTSPOT -
Hot Area:
Correct Answer:
Reference:
https://docs.microsoft.com/en-gb/azure/cognitive-services/text-analytics/overview https://azure.microsoft.com/en-gb/services/cognitive-
services/speech-services/
  Sabba Highly Voted  2 weeks ago

I think it is N/Y/N.
upvoted 5 times
  dukejan 1 week, 6 days ago

l agree
upvoted 2 times
  Awot Most Recent  3 days, 8 hours ago

The answer is Correct.
Visit the second link on the answer page.
upvoted 1 times
  xiandasu 6 days, 18 hours ago

the second websit of ref shows these three functions in speech service.
upvoted 1 times
  xiandasu 6 days, 18 hours ago

https://azure.microsoft.com/en-gb/services/cognitive-services/speech-services/
upvoted 1 times

Transcribe a call to text -Speech Service: Speech to Text Service
Extract call Transcription to find key entity - Text Analytic : Entity Recognition
Translate a call to different langauge : Speech Service : Speech Translations
Thus Y/ Y /Y
upvoted 1 times
  Lipseal 1 week, 2 days ago

Speech translation -
A Speech service feature that translates speech in real time
Translate audio from more than 30 languages https://azure.microsoft.com/en-gb/services/cognitive-services/speech-translation/
upvoted 1 times
  Oopsie 1 week, 3 days ago

I think the last one is N?
upvoted 1 times
  anil_kapoor 1 week, 5 days ago

speech service can translate as well?
upvoted 2 times
  xcesaro1096 1 week, 6 days ago

Same as Sabba. mmmmmm
upvoted 2 times
Your website has a chatbot to assist customers.

You need to detect when a customer is upset based on what the customer types in the chatbot.
Which type of AI workload should you use?
A. anomaly detection
B. semantic segmentation
C. regression
D. natural language processing
Correct Answer: D
Reference:

ans is correct
upvoted 9 times

NLP is correct,thats sentiment analysis
upvoted 2 times

NLP is correct
upvoted 2 times
  NoNameP 1 month, 1 week ago

Answer is correct (D)
upvoted 2 times
  Zhubajie 1 month, 2 weeks ago

In computer vision, the task of masking out pixels belonging to different classes of objects such as background or people is referred to as semantic
segmentation.
https://azure.microsoft.com/es-es/blog/how-to-extract-building-footprints-from-satellite-images-using-deep-learning/
upvoted 2 times
  danflr 5 months, 1 week ago

I'm wondering why language understanding service (LUIS) is not mentioned here, as i comes with sentiment anlysis. https://docs.microsoft.com/en-
us/azure/cognitive-services/luis/luis-reference-prebuilt-sentiment?tabs=english
upvoted 1 times

Because its a service under the Natural Language Processing AI Workload not a Workload on is own.
upvoted 1 times

it's part of natural language processing
upvoted 3 times
  RaulDuke 5 months, 3 weeks ago

Also semantic segmentation could be used to idenfity if it is posivite or negative messages. So I would consider either B & D.
upvoted 2 times

Sentiment Analysis is used to identify if it's positive, negative or neutral... Not semantic segmentation.
upvoted 6 times
  akpe 3 months, 3 weeks ago

semantic segmentation is for computer vision and not for Natural language processing.
upvoted 8 times
You plan to develop a bot that will enable users to query a knowledge base by using natural language processing.
Which two services should you include in the solution? Each correct answer presents part of the solution.
A. QnA Maker
B. Azure Bot Service
C. Form Recognizer
D. Anomaly Detector
Correct Answer: AB
Reference:
https://docs.microsoft.com/en-us/azure/bot-service/bot-service-overview-introduction?view=azure-bot-service-4.0
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/choose-natural-language-processing-service
  Emdy 1 week, 3 days ago

Correct
upvoted 1 times
You need to provide content for a business chatbot that will help answer simple user queries.
What are three ways to create question and answer text by using QnA Maker? Each correct answer presents a complete solution.
A. Generate the questions and answers from an existing webpage.
B. Use automated machine learning to train a model based on a file that contains the questions.
C. Manually enter the questions and answers.
D. Connect the bot to the Cortana channel and ask questions by using Cortana.
E. Import chit-chat content from a predefined data source.
Correct Answer: ACE

Automatic extraction -
Extract question-answer pairs from semi-structured content, including FAQ pages, support websites, excel files, SharePoint documents, product
manuals and policies.
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/concepts/content-types
  shri77 Highly Voted  3 months, 1 week ago

ACE are correct answers.
upvoted 8 times
  Emdy Most Recent  1 week, 3 days ago

Answers are correct
https://docs.microsoft.com/en-us/learn/modules/build-faq-chatbot-qna-maker-azure-bot-service/2-get-started-qna-bot
upvoted 1 times

ACE is correct
upvoted 1 times
  Emixmini 4 months, 2 weeks ago

I have a doubt about these answers. Shouldn't be ABE ?
upvoted 1 times
  EricSon 3 months, 2 weeks ago

“B” only provides the questions without answers
upvoted 5 times

After provisioning a QnA Maker resource, you can use the QnA Maker portal to create a knowledge base that consists of question-and-answer
pairs. These questions and answers can be:
Generated from an existing FAQ document or web page.
Imported from a pre-defined chit-chat data source.
Entered and edited manually.

upvoted 3 times

ACE are correct
upvoted 3 times
You have a frequently asked questions (FAQ) PDF file.

You need to create a conversational support system based on the FAQ.
A. QnA Maker
B. Text Analytics
C. Computer Vision
Correct Answer: A
QnA Maker is a cloud-based API service that lets you create a conversational question-and-answer layer over your existing data. Use it to build a
knowledge base by extracting questions and answers from your semi-structured content, including FAQs, manuals, and documents.
Reference:
https://azure.microsoft.com/en-us/services/cognitive-services/qna-maker/
  Parre89 Highly Voted  1 month, 3 weeks ago

A is correct
upvoted 5 times

A is correct
upvoted 5 times
  shri77 Most Recent  3 months, 1 week ago

correct Answer
upvoted 4 times

Correct Answer
upvoted 3 times

Correct Answer
upvoted 3 times
You need to reduce the load on telephone operators by implementing a chatbot to answer simple questions with predefined answers.
Which two AI service should you use to achieve the goal? Each correct answer presents part of the solution.
A. Text Analytics
B. QnA Maker
C. Azure Bot Service
D. Translator Text
Correct Answer: BC
Bots are a popular way to provide support through multiple communication channels. You can use the QnA Maker service and Azure Bot Service
to create a bot that answers user questions.
Reference:
https://docs.microsoft.com/en-us/learn/modules/build-faq-chatbot-qna-maker-azure-bot-service/
  MarcoMarcoMarco 1 month, 3 weeks ago

Correct but ill posed. Azure BOT is a way to distribute conversational AI models to make final interaction easy.. But it is not an AI service by itself, it
is more like a connector/interface
upvoted 3 times
  LIBERCOSOFT 2 weeks, 6 days ago

It's indicated that one answer present part of the solution.
upvoted 2 times

Answer is correct
upvoted 2 times

correct answer obviously B and C
upvoted 1 times

Right answer!
upvoted 1 times

answer is correct
upvoted 2 times

answer is correct
upvoted 3 times
Which two scenarios are examples of a conversational AI workload? Each correct answer presents a complete solution.
A. a smart device in the home that responds to questions such as ‫ג‬€What will the weather be like today?‫ג‬€
B. a website that uses a knowledge base to interactively respond to users‫ג‬€™ questions
C. assembly line machinery that autonomously inserts headlamps into cars
D. monitoring the temperature of machinery to turn on a fan when the temperature reaches a specific threshold
Correct Answer: AB
  emphasis Highly Voted  7 months ago

the given answer is correct
upvoted 10 times
  O_Anjum Most Recent  3 weeks, 3 days ago

A is LUIS, and C & D just do not qualify as chat bots.
upvoted 1 times

the answer is correct
upvoted 2 times

upvoted 2 times
You have the process shown in the following exhibit.
Which type AI solution is shown in the diagram?
A. a sentiment analysis solution
B. a chatbot
C. a machine learning model
D. a computer vision application
Correct Answer: B
  JIep4uk Highly Voted  3 months, 3 weeks ago

the funniest thing that Chat bot is written on the top of picture in this question XD
upvoted 19 times
  Daves2ng 1 month ago

honestly, I didn't notice that until you pointed it out.
Answer is definitely chatbot
upvoted 2 times

Not the first time I've seen this in MS Exams.
upvoted 1 times
  tearcodiac Highly Voted  3 months, 2 weeks ago

lol the question has its answer
upvoted 7 times
  Lewikeezy Most Recent  2 months ago

LOL I wish all questions come out with the answer inscribed somewhere, obviously the answer is chatbot (option B)
upvoted 2 times

Chatbot
upvoted 2 times

B is correct
upvoted 5 times
You need to develop a web-based AI solution for a customer support system. Users must be able to interact with a web app that will guide them to
the best resource or answer.
A. Custom Vision
B. QnA Maker
C. Translator Text
D. Face
Correct Answer: B
QnA Maker is a cloud-based API service that lets you create a conversational question-and-answer layer over your existing data. Use it to build a
knowledge base by extracting questions and answers from your semi-structured content, including FAQs, manuals, and documents. Answer
users‫ג‬€™ questions with the best answers from the QnAs in your knowledge base‫ג‬€"automatically. Your knowledge base gets smarter, too, as it
continually learns from user behavior.
Incorrect Answers:
A: Azure Custom Vision is a cognitive service that lets you build, deploy, and improve your own image classifiers. An image classifier is an AI
service that applies labels (which represent classes) to images, according to their visual characteristics. Unlike the Computer Vision service,
Custom Vision allows you to specify the labels to apply.
D: Azure Cognitive Services Face Detection API: At a minimum, each detected face corresponds to a faceRectangle field in the response. This
set of pixel coordinates for the left, top, width, and height mark the located face. Using these coordinates, you can get the location of the face
and its size. In the API response, faces are listed in size order from largest to smallest.
Reference:
https://azure.microsoft.com/en-us/services/cognitive-services/qna-maker/

Correct
upvoted 3 times

the answer is correct
upvoted 2 times

anser is correct
upvoted 3 times
Which AI service should you use to create a bot from a frequently asked questions (FAQ) document?
A. QnA Maker
B. Language Understanding (LUIS)
C. Text Analytics
D. Speech
Correct Answer: A

A is correct
upvoted 6 times
  olowoyinka Most Recent  3 months, 2 weeks ago

upvoted 1 times

the given answer is correct
upvoted 1 times
HOTSPOT -
Hot Area:
Correct Answer:
With Microsoft‫ג‬€™s Conversational AI tools developers can build, connect, deploy, and manage intelligent bots that naturally interact with their
users on a website, app, Cortana, Microsoft Teams, Skype, Facebook Messenger, Slack, and more.
Reference:
https://azure.microsoft.com/en-in/blog/microsoft-conversational-ai-tools-enable-developers-to-build-connect-and-manage-intelligent-bots

Correct one
upvoted 3 times
  jowep90331 2 months, 2 weeks ago

Correct
upvoted 2 times

Correct
upvoted 1 times

Answer is correct
upvoted 1 times

answer is correct
upvoted 4 times
Which scenario is an example of a webchat bot?
A. Determine whether reviews entered on a website for a concert are positive or negative, and then add a thumbs up or thumbs down emoji to
the reviews.
B. Translate into English questions entered by customers at a kiosk so that the appropriate person can call the customers back.
C. Accept questions through email, and then route the email messages to the correct person based on the content of the message.
D. From a website interface, answer common questions about scheduled events and ticket purchases for a music festival.
Correct Answer: D
  Feyisara Highly Voted  2 months, 2 weeks ago

Very correct answer
upvoted 5 times
  101_dummy Most Recent  1 month, 1 week ago

D is correct
upvoted 3 times
  Parre89 1 month, 3 weeks ago

D is correct
upvoted 2 times

Correct
upvoted 2 times
  Minghon 3 months, 2 weeks ago

upvoted 2 times

ans is correct
upvoted 4 times
HOTSPOT -
Hot Area:
Correct Answer:
Reference:
https://docs.microsoft.com/en-gb/azure/cognitive-services/qnamaker/concepts/data-sources-and-content https://docs.microsoft.com/en-
us/azure/cognitive-services/luis/choose-natural-language-processing-service
  Jedi_sg2000 6 days, 19 hours ago

LUIS determines the intent of a user's text (known as an utterance), while QnA Maker determines the answer to a user's text (known as a query).
Utterance is for LUIS , not QnA
upvoted 1 times
  Danrab 1 week ago

I'd say N/Y/Y...
upvoted 1 times
HOTSPOT -
Hot Area:
Correct Answer:
Reference:
https://docs.microsoft.com/en-us/azure/bot-service/bot-service-manage-channels?view=azure-bot-service-4.0
HOTSPOT -
Hot Area:
Correct Answer:
Reference:
  Zappy987654321 5 days, 9 hours ago

Correct answer would be Y-Y-N
upvoted 1 times
  Mysticguy 1 week, 6 days ago

Connect your bot to channels such as Facebook, Messenger, Kik, Slack, Microsoft Teams, Telegram, text/SMS, Twilio, and Cortana. So Y/Y/Y
upvoted 1 times
  Sabba 2 weeks ago

I think it is Y/Y/N.
upvoted 2 times
  dukejan 1 week, 4 days ago

I agree. The big does not connect to external resources
upvoted 1 times
Which two scenarios are examples of a conversational AI workload? Each correct answer presents a complete solution.
A. a telephone answering service that has a pre-recorder message
B. a chatbot that provides users with the ability to find answers on a website by themselves
C. telephone voice menus to reduce the load on human resources
D. a service that creates frequently asked questions (FAQ) documents by crawling public websites
Correct Answer: BC
B: A bot is an automated software program designed to perform a particular task. Think of it as a robot without a body.
C: Automated customer interaction is essential to a business of any size. In fact, 61% of consumers prefer to communicate via speech, and
most of them prefer self-service. Because customer satisfaction is a priority for all businesses, self-service is a critical facet of any customer-
facing communications strategy.
Incorrect Answers:
D: Early bots were comparatively simple, handling repetitive and voluminous tasks with relatively straightforward algorithmic logic. An example
would be web crawlers used by search engines to automatically explore and catalog web content.
Reference:
https://docs.microsoft.com/en-us/azure/architecture/data-guide/big-data/ai-overview https://docs.microsoft.com/en-
us/azure/architecture/solution-ideas/articles/interactive-voice-response-bot

ans is correct
upvoted 6 times
  ptomasi Most Recent  2 weeks, 6 days ago

I temp to say A, B
A. a telephone answering service that has a pre-recorder message
C is not correct as voice menus are not operated as conversation from users perspective but using keypad for choice
upvoted 1 times
  Derin_tade 2 weeks, 5 days ago

Hey mate, A pre-recorder message is just one way... You can only listen without giving back a response... But voice menus on the other hand
allow you to respond to the voice you're listening to even though you might not be saying your answers but when you press whatever button
you are responding to the bot and it can interpret your response and give you feedback... So I think C is a better choice than A... Also think
there'd be voice menus that can listen to voices as feedback.
upvoted 1 times
  PGG 1 month, 1 week ago

I will argue that D justification is wrong...check out GPT-3...it's train doing a webcrawling is as today is the most complex IA in the world...but
well...you can't make it by using Azure Virtual Agents or Chat Bot, it's a transformer NLP, DNN model
upvoted 1 times

https://getvoip.com/blog/2020/10/19/conversational-ai/ Hard to pick an answer.
upvoted 1 times

i think B and C are the correct options,obviously both have to do with conversation and the telephone service like the AI chatbot reduces the direct
human to human interaction levels with some custom buttons offering some form of solution you may get your answers before having to talk to a
human recipient or responder, so it is "BC" for me
upvoted 1 times

In my opinion it's
D. a service that creates frequently asked questions (FAQ) documents by crawling public websites
upvoted 2 times
  O_Anjum 3 weeks, 4 days ago

I eliminated D as the question says "<i>conversational AI workload<i>"
upvoted 1 times

answer is correct
upvoted 2 times
HOTSPOT -
Hot Area:
Correct Answer:
Box 1: Yes -
Azure bot service can be integrated with the powerful AI capabilities with Azure Cognitive Services.
Box 2: Yes -
Azure bot service engages with customers in a conversational manner.
Box 3: No -
The QnA Maker service creates knowledge base, not question and answers sets.
Note: You can use the QnA Maker service and a knowledge base to add question-and-answer support to your bot. When you create your
knowledge base, you seed it with questions and answers.
Reference:
https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-tutorial-add-qna
  Kheops98 Highly Voted  3 months, 2 weeks ago

Isn't the QnA Maker part of the Azure Bot Services? My answer would be Y/Y/Y based on: https://azure.microsoft.com/en-us/services/bot-
services/#features
upvoted 8 times
  EricSon 3 months, 2 weeks ago

Not exactly. You create a Bot that “points” to the knowledge base imported using QnA Maker.
upvoted 4 times
  Lewikeezy Highly Voted  2 months ago

On critical reasoning, I think the given answer is correct, YES, YES and NO respectively since the BOT has to be pointed to the QnA maker
upvoted 5 times
  vmontalvao Most Recent  2 months, 3 weeks ago

If you create a custom Azure Bot Service you can use your own QnA Maker KB so last answer should be YES.
upvoted 2 times

answer is correct
upvoted 5 times
You have a webchat bot that provides responses from a QnA Maker knowledge base.
You need to ensure that the bot uses user feedback to improve the relevance of the responses over time.
What should you use?
A. key phrase extraction
B. sentiment analysis
C. business logic
D. active learning
Correct Answer: D
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/how-to/improve-knowledge-base
You are developing a conversational AI solution that will communicate with users through multiple channels including email, Microsoft Teams,
and webchat.
A. Text Analytics
B. Azure Bot Service
C. Translator
D. Form Recognizer
Correct Answer: B
Reference:
HOTSPOT -
Hot Area:
Correct Answer:
Reference:
  dukejan Highly Voted  1 week, 4 days ago

I think this should be y/n/n
upvoted 5 times
  AntonioCosta77 1 week, 4 days ago

me too
upvoted 2 times
  Oopsie 1 week, 3 days ago

Same!!!
upvoted 1 times

Should be Y-Y-Y.
[Reference] https://docs.microsoft.com/en-us/azure/bot-service/bot-service-overview-introduction?view=azure-bot-service-4.0
"A bot can be thought of as a web application that has a conversational interface. A user connects to a bot though a channel such as Facebook,
Slack, or Microsoft Teams...
Depending on how the bot is configured and how it is registered with the channel, users can interact with the bot through text or speech, and the
conversation might include images and video....
Bots can do the same things other types of software can do - read and write files, use databases and APIs, and do the regular computational tasks.
"
upvoted 1 times
  AZ900test 3 days, 5 hours ago

My answer is Y-N-N
upvoted 2 times

I think it should be Y/N/N
upvoted 2 times
  AZ900test 1 week, 1 day ago

I agree with comments above , answer should be Y-N-N
upvoted 3 times

AI 900 Exam Free Actual Q As Page 1 ExamTopics PDF

Uploaded by

Copyright:

Available Formats

AI 900 Exam Free Actual Q As Page 1 ExamTopics PDF

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

AI 900 Exam Free Actual Q As Page 1 ExamTopics PDF

Uploaded by

Copyright:

Available Formats

6/17/2021 AI-900 Exam – Free Actual Q&As, Page 1 | ExamTopics

- Expert Verified, Online, Free.

 Custom View Settings

Topic 1 - Single Topic

B. a reduced workload for the customer service agents

C. improved product reliability

  abhi0706 Highly Voted  8 months, 1 week ago

  ksarhan Highly Voted  8 months ago

  berserkguts Most Recent  2 weeks, 1 day ago

  SQLNh 1 month ago

  freshmaker 1 month, 1 week ago

  sandykond 1 month, 1 week ago

  LPatel 1 month, 2 weeks ago

  saksam89 1 month, 2 weeks ago

  techifiedMercy 1 month, 3 weeks ago

  Ash111 2 months, 1 week ago

  Samiat 2 months, 2 weeks ago

  vickkywyze 2 months, 2 weeks ago

  cron0001 2 months, 2 weeks ago

  hibana2077 2 months, 2 weeks ago

  ShefAZ 2 months, 3 weeks ago

  Floxzy 2 months, 3 weeks ago

  agsite 2 months, 3 weeks ago

A. Use features for training and labels for evaluation.

C. Use labels for training and features for evaluation.

Correct Answer: Answer: B

  ExamPwnr Highly Voted  8 months, 2 weeks ago

  amvi Highly Voted  8 months, 2 weeks ago

  berserkguts Most Recent  2 weeks, 1 day ago

  AshishScotia 2 weeks, 3 days ago

  Ajao 1 month ago

  SQLNh 1 month ago

  freshmaker 1 month, 1 week ago

  Rishubelgium 1 month, 1 week ago

  kheiro 1 month, 1 week ago

  Kanjati 1 month, 1 week ago

  Ebenezer 1 month, 2 weeks ago

  techifiedMercy 1 month, 3 weeks ago

  CherryCarpo 2 months ago

  Ifexalex 2 months, 1 week ago

  vickkywyze 2 months, 2 weeks ago

  cron0001 2 months, 2 weeks ago

  ShefAZ 2 months, 3 weeks ago

  Vijaya Highly Voted  8 months, 2 weeks ago

  denizej Highly Voted  7 months, 3 weeks ago

  SnowCheetah Most Recent  1 week, 4 days ago

  berserkguts 2 weeks, 1 day ago

  AshishScotia 2 weeks, 2 days ago

  Kanjati 1 month ago

  Kanjati 1 month ago

  freshmaker 1 month, 1 week ago

  afzal95 2 months, 1 week ago

  cron0001 2 months, 2 weeks ago

  pooja11284 2 months, 2 weeks ago

  ShefAZ 2 months, 3 weeks ago

  Nandy_Shree 2 months, 3 weeks ago

  CollinsMarcus 2 months, 3 weeks ago

  Arocmd9 2 months, 4 weeks ago

  lvbranco 3 months, 3 weeks ago