Code No: R2032051 R20 SET -1

III B. Tech II Semester Regular Examinations, July -2023

MACHINE LEARNING
(Com. to CSE & IT)
Time: 3 hours Max. Marks: 70
Answer any FIVE Questions ONE Question from Each unit
All Questions Carry Equal Marks
*****

UNIT-I
1. a) Can you name and explain four of the main challenges in Machine Learning? [7M]
b) Differentiate traditional and machine learning approaches with neat sketches. [7M]
(OR)
2. a) List and explain Risk statistics. [7M]
b) Explain Training and Test Loss while generating the models. [7M]
UNIT-II
3. a) What are General Linear Models? Give their parametric equations. [7M]
b) Explain about ANOVA in detail. [7M]
(OR)
4. a) What is the Role of Distance Measures ML Algorithms? Illustrate. [7M]
b) Explain KNN algorithm with an example. [7M]
UNIT-III
5. a) What is the difference between hard and soft voting classifiers? Explain them. [7M]
b) Define Boosting? Explain about Ada Boosting technique. [7M]
(OR)
6. a) Explain about Linear SVM Classification in detail. Compare it with nonlinear [7M]
model.
b) Describe Gaussian RBF kernel in SVM. [7M]
UNIT-IV
7. a) Describe K means clustering algorithm. [7M]
b) Using K means clustering algorithm form two clusters for given data. [7M]
Height 18 17 16 17 18 18 18 18 18 18 18 17
5 0 8 9 2 8 0 0 3 0 0 7
Weight 72 56 60 68 72 77 71 70 84 88 67 76
(OR)
8. a) What is Curse of Dimensionality? How to find the solution for it? Explain. [7M]
b) Explain about Kernel PCA in detail. [7M]
UNIT-V
9. a) How Biological Neurons related to ANN? Explain. [7M]
b) With neat sketch explain Loading and preprocessing data from multiple CSV [7M]
files?
(OR)
10. a) Name three popular activation functions. Can you draw and explain them? [7M]
b) Explain about the step-by-step procedure to install TensorFlow 2. [7M]

1 of 1

|''|'||||''|'''|||'|
 Code No: R2032051
R2031011
R2031351
R203135A
R203147A
R203147C
R203105O
P2031051 R20 SET
SET
RA--22

III B. Tech II Semester Regular Examinations, July -2023

MACHINE LEARNING
(Com. to CSE & IT)
Time: 3 hours Max. Marks: 70
Answer any FIVE Questions ONE Question from Each unit
All Questions Carry Equal Marks
*****

UNIT-I
1. a) What is Machine Learning? Explain any four applications with an example. [7M]
b) Write the differences between Artificial Intelligence, Machine Learning and [7M]
Deep Learning.
(OR)
2. a) Explain Tradeoffs in Statistical Learning. [7M]
b) What is the importance of Probability and Statistics while generating [7M]
supervised or unsupervised model? Explain.
UNIT-II
3. a) What is the decision tree? How to choose attribute selection in decision tree? [7M]
b) Explain about Decision tree classifier with an example. [7M]
(OR)
4. a) Can Logistic regression be used for classification or regression? Discuss about [7M]
Logistic Regression algorithm.
b) Explain about MNIST dataset. Describe the procedure to apply classification [7M]
technique.
UNIT-III
5. a) What are the benefits of out-of-bag evaluation? Explain it. [7M]
b) Discuss about Extra trees. Are Extra-Trees slower or faster than regular [7M]
Random Forests? Explain.
(OR)
6. a) Define Non-linear classification. Explain the list of kernels in SVM briefly. [7M]
b) Explain SVM regression in detail with a neat diagram. [7M]
UNIT-IV
7. a) What is Density based clustering? Describe DBSCAN clustering algorithm. [7M]
b) How can we use clustering for Preprocessing? Explain. [7M]
(OR)
8. a) What are the main motivations for reducing a dataset’s dimensionality? What [7M]
are the main drawbacks?
b) In what cases would you use Incremental PCA, Randomized PCA & Kernel [7M]
PCA? Explain.
UNIT-V
9. a) Explain about Logical Computations with Neurons. [7M]
b) Differentiate Forward and Backward propagations in ANN . [7M]
(OR)
10. a) Why would you want to use the Data API? Explain about Data API? [7M]
b) Illustrate the two types of implementation of Keras API. [7M]

1 of 1

|''|'||||''|'''|||'|
 Code No: R203147C
R2031011
R2031351
R203135A
R203147A
R203105O
P2031051
R2032051 R20 SET
SET
RA--32

III B. Tech II Semester Regular Examinations, July -2023

MACHINE LEARNING
(Com. to CSE & IT)
Time: 3 hours Max. Marks: 70
Answer any FIVE Questions ONE Question from Each unit
All Questions Carry Equal Marks
*****

UNIT-I
1. a) What is Batch and online learning system? Explain. [7M]
b) Would you frame the problem of spam detection as a supervised learning [7M]
problem or an unsupervised learning problem? Explain.
(OR)
2. a) What is Empirical Risk Minimization? Explain Estimating the risk using cross [7M]
validation.
b) Define and explain Optimal prediction function for Squared Error Loss. [7M]
UNIT-II
3. a) What is Bayes theorem? Explain Naïve bayes with an example. [7M]
b) What is ranking in binary classification in Machine Learning? What is the best [7M]
algorithm for raking?
(OR)
4. a) What is the purpose of sigmoid function in Logistic Regression? Explain. [7M]
b) Discuss about multi class classification technique. [7M]
UNIT-III
5. a) What is Bagging and pasting? Explain it’s implementation with scikit-learn. [7M]
b) Define Boosting? Explain about Gradient Boosting technique. [7M]
(OR)
6. a) What are support vectors? Describe Large margin classification in SVM. [7M]
b) Explain about Naïve Bayes classifier algorithm with an example. [7M]
UNIT-IV
7. a) How can we use clustering for image segmentation? Explain. [7M]
b) What is a Gaussian mixture? What tasks can you use it for? Explain. [7M]
(OR)
8. a) Explain the process of reducing the dimension by using Manifold Learning. [7M]
b) Can PCA be used to reduce the dimensionality of a highly nonlinear dataset? [7M]
Explain
UNIT-V
9. a) Explain about Perceptron ANN architecture with a neat sketch. [7M]
b) Elaborate the steps in processing data with TensorFlow. [7M]
(OR)
10. a) What are the benefits of splitting a large dataset into multiple files? Explain [7M]
about tf.keras while using dataset?
b) With neat sketch explain Chaining dataset transformations. [7M]

1 of 1

|''|'||||''|'''|||'|
 Code No: R2032051
R2031011
R2031351
R203135A
R203147A
R203147C
R203105O
P2031051 R20 SET
SET
RA--42

III B. Tech II Semester Regular Examinations, July -2023

MACHINE LEARNING
(Com. to CSE & IT)
Time: 3 hours Max. Marks: 70
Answer any FIVE Questions ONE Question from Each unit
All Questions Carry Equal Marks
*****

UNIT-I
1. a) Compare and contrast Instance-Based and Model-Based Learning [7M]
b) Explain the process of Machine Learning step by step. [7M]
(OR)
2. a) What is Empirical Risk Minimization? Explain Regularized and Structural risk [7M]
minimizations?
b) Write about Sampling distribution of an estimator. [7M]
UNIT-II
3. a) Write and explain Linear regression with an example. [7M]
b) What is the Sigmoid function? Where it can be used? Explain. [7M]
(OR)
4. a) What is Overfitting? Explain about SVM algorithm to overcome it? [7M]
b) Discuss about Linear regression with an example. [7M]
UNIT-III
5. a) Illustrate the stacking mechanism in ensemble techniques. [7M]
b) What is Bagging technique? Explain about Random Forest Algorithm. [7M]
(OR)
6. a) What is Linear classifier? Explain SVM linear classification. [7M]
b) What is Kernel trick? Describe polynomial kernel function. [7M]
UNIT-IV
7. a) What are the main applications of clustering algorithms? Illustrate. [7M]
b) How can we use clustering for semi-supervised learning? Explain [7M]
(OR)
8. a) Explain the concept of PCA for Compression. [7M]
b) How can you evaluate the performance of a dimensionality reduction algorithm [7M]
on your dataset? Explain.
UNIT-V
9. a) Explain about Multi Layer Perceptron (MLP) ANN architecture. [7M]
b) How is data loaded with TesorFlow? Illustrate the steps. [7M]
(OR)
10. a) What types of neural network layers does Keras support? Explain them. [7M]
b) Discuss about shuffle() method in Keras. [7M]

1 of 1

|''|'||||''|'''|||'|