10/27/24, 1:12 PM Deep Learning - IIT Ropar - - Unit 4 - Week 1

(https://swayam.gov.in) (https://swayam.gov.in/nc_details/NPTEL)

vmcse09@gmail.com 

NPTEL (https://swayam.gov.in/explorer?ncCode=NPTEL) » Deep Learning - IIT Ropar (course)

Course Week 1 : Assignment 1

outline The due date for submitting this assignment has passed.
Due on 2024-08-07, 23:59 IST.
About
NPTEL ()
Assignment submitted on 2024-08-04, 03:49 IST
How does an 1) Consider the following table, where x 1 and x 2 are features and y is a label 1 point
NPTEL
online
course
work? ()

Week 1 ()

Biological
Neuron (unit?
unit=17&lesso
n=18)
Assume that the elements in w are initialized to zero and the perception learning algorithm is
From Spring to used to update the weights w . If the learning algorithm runs for long enough iterations, then
Winter of AI
(unit? The algorithm never converges
unit=17&lesso
The algorithm converges (i.e., no further weight updates) after some iterations
n=19)
The classification error remains greater than zero
The Deep
The classification error becomes zero eventually
Revival (unit?
unit=17&lesso Partially Correct.
n=20) Score: 0.5
Accepted Answers:
From Cats to The algorithm converges (i.e., no further weight updates) after some iterations
Convolutional
The classification error becomes zero eventually
Neural
Networks
(unit?
2) In the perceptron model, the weight w vector is perpendicular to the linear decision 1 point
boundary at all times.

https://onlinecourses.nptel.ac.in/noc24_cs114/unit?unit=17&assessment=280 1/8
10/27/24, 1:12 PM Deep Learning - IIT Ropar - - Unit 4 - Week 1

unit=17&lesso True
n=21)
False
Faster, higher,
Yes, the answer is correct.
stronger (unit?
Score: 1
unit=17&lesso
Accepted Answers:
n=22)
True
The Curious
3) What is the perceptron algorithm used for? 1 point
Case of
Sequences
Clustering data points
(unit?
unit=17&lesso Classifying data
n=23) Solving optimization problems

Beating Finding the shortest path in a graph

humans at
Yes, the answer is correct.
their own Score: 1
games Accepted Answers:
(literally) (unit? Classifying data
unit=17&lesso
n=24)
4) Choose the correct input-output pair for the given MP Neuron. 1 point
The Madness 1, if x 1 + x 2 + x 3 > 2
f (x) = {
(2013-) (unit? 0, otherwise
unit=17&lesso
n=25)
y = 1 for (x 1 , x 2 , x 3 ) = (0, 1, 1)
(Need for)
Sanity (unit? y = 0 for (x 1 , x 2 , x 3 ) = (0, 0, 1)
unit=17&lesso
n=26)
y = 1 for (x 1 , x 2 , x 3 ) = (0, 0, 0)

Motivation
from Biological y = 1 for (x 1 , x 2 , x 3 ) = (1, 1, 1)

Neurons (unit?
unit=17&lesso y = 0 for (x 1 , x 2 , x 3 ) = (1, 0, 1)

n=27)
Yes, the answer is correct.
McCulloch Score: 1
Pitts Neuron, Accepted Answers:
y = 0 for (x 1 , x 2 , x 3 ) = (0, 0, 1)
Thresholding
Logic (unit? y = 1 for (x 1 , x 2 , x 3 ) = (1, 1, 1)

unit=17&lesso y = 0 for (x 1 , x 2 , x 3 ) = (1, 0, 1)

n=28)

Perceptrons
5) Which of the following Boolean functions can be implemented using a perceptron? 1 point
(unit?
NOR
unit=17&lesso
n=29) NAND

Error and Error

NOT
Surfaces XOR
(unit?
Yes, the answer is correct.
unit=17&lesso Score: 1
n=30)
Accepted Answers:
Perceptron NOR
Learning NAND
Algorithm NOT

https://onlinecourses.nptel.ac.in/noc24_cs114/unit?unit=17&assessment=280 2/8
10/27/24, 1:12 PM Deep Learning - IIT Ropar - - Unit 4 - Week 1

(unit? 6) Which of the following threshold values of MP neuron implements AND Boolean 1 point
unit=17&lesso function? Assume that the number of inputs to the neuron is 7 and the neuron does not have any
n=31) inhibitory inputs.
Proof of
Convergence 1
of Perceptron
Learning 3

Algorithm
6
(unit?
unit=17&lesso
7
n=32)
8
Lecture
Material for Yes, the answer is correct.
Score: 1
Week 1 (unit?
unit=17&lesso
Accepted Answers:
7
n=33)

Quiz: Week 1 7) Suppose we have a boolean function that takes 4 inputs x 1 , x 2 , x 3 , x 4 ? We have 1 point
: Assignment an MP neuron with parameter θ = 3 . For how many inputs will this MP neuron give output
1 y = 1 ?
(assessment?
name=280)
5

Week 1
4
Feedback
Form: Deep
1
Learning - IIT
Ropar (unit? 16
unit=17&lesso
Yes, the answer is correct.
n=35) Score: 1
Accepted Answers:
Week 2 () 5

Week 3 () 8) −1 1 point
Consider points shown in the picture. The vector w = [ ] . As per this weight
−1

week 4 () vector, the Perceptron algorithm will predict which classes for the data points x 1 and x 2 .

Week 5 () NOTE:

Week 6 ()

Week 7 ()

Week 8 ()

Week 9 ()

week 10 ()

Week 11 ()

Week 12 ()

https://onlinecourses.nptel.ac.in/noc24_cs114/unit?unit=17&assessment=280 3/8
10/27/24, 1:12 PM Deep Learning - IIT Ropar - - Unit 4 - Week 1

T
1 if w x > 0
Download y = {
T
−1 if w x ≤ 0
Videos ()

Books ()

Text
Transcripts
()

Problem
Solving
Session -
July 2024 ()

x 1 = −1

x1 = 1

x 2 = −1

x2 = 1

Yes, the answer is correct.

Score: 1
Accepted Answers:
x 1 = −1
x2 = 1

9) Consider the following table, where x 1 and x 2 are features (packed into a single 1 point
x1
vector x = [ ] ) and y is a label:
x2

Suppose that the perceptron model is used to classify the data points. Suppose further that the

https://onlinecourses.nptel.ac.in/noc24_cs114/unit?unit=17&assessment=280 4/8
10/27/24, 1:12 PM Deep Learning - IIT Ropar - - Unit 4 - Week 1

1
weights w are initialized to w = [ ] . The following rule is used for classification,
1

T
1 if w x > 0
y = {
T
0 if w x ≤ 0

The perceptron learning algorithm is used to update the weight vector w . Then, how many times
the weight vector w will get updated during the entire training process?

2
1
0
Not possible to determine
Yes, the answer is correct.
Score: 1
Accepted Answers:
0

10) Which Boolean function with two inputs x1 and x2 is represented by the following 1 point
decision boundary? (Points on boundary or right of the decision boundary to be classified 1)

AND
OR
XOR
NAND

Yes, the answer is correct.

Score: 1
Accepted Answers:
OR

11) Choose the correct input-output pair for the given MP Neuron. 1 point

1, if x1 + x2 + x3 ≥ 2
y = {
0, otherwise

y = 1 for (x 1 , x 2 , x 3 ) = (0, 1, 1)

y = 0 for (x 1 , x 2 , x 3 ) = (0, 0, 1)

y = 1 for (x 1 , x 2 , x 3 ) = (1, 1, 1)

https://onlinecourses.nptel.ac.in/noc24_cs114/unit?unit=17&assessment=280 5/8
10/27/24, 1:12 PM Deep Learning - IIT Ropar - - Unit 4 - Week 1

y = 0 for (x 1 , x 2 , x 3 ) = (1, 0, 0)

Yes, the answer is correct.

Score: 1
Accepted Answers:
y = 1 for (x 1 , x 2 , x 3 ) = (0, 1, 1)

y = 0 for (x 1 , x 2 , x 3 ) = (0, 0, 1)

y = 1 for (x 1 , x 2 , x 3 ) = (1, 1, 1)

y = 0 for (x 1 , x 2 , x 3 ) = (1, 0, 0)

12) Suppose we have a boolean function that takes 4 inputs x1, x2, x3, x4? We have an 1 point
MP neuron with parameter θ = 2 . For how many inputs will this MP neuron give output y = 1?

11
21
15
8

Yes, the answer is correct.

Score: 1
Accepted Answers:
11

13) We are given the following data: 1 point

Can you classify every label correctly by training a perceptron algorithm? (assume bias to be 0
while training)

Yes
No

Yes, the answer is correct.

Score: 1
Accepted Answers:
No

14) We are given the following dataset with features as (x1,x2) and y as the label (-1,1). 1 point
If we apply the perception algorithm on the following dataset with w initialized as (0,0). What will

https://onlinecourses.nptel.ac.in/noc24_cs114/unit?unit=17&assessment=280 6/8
10/27/24, 1:12 PM Deep Learning - IIT Ropar - - Unit 4 - Week 1

be the value of w when the algorithm converges? (Start the algorithm from (2,2)

(-2,2)
(2,1)
(2,-1)
None of These

Yes, the answer is correct.

Score: 1
Accepted Answers:
(2,-1)

15) Consider points shown in the picture. The vector w is (-1,0). As per this weight 1 point
vector, the Perceptron algorithm will predict which classes for the data points x1 and x2.

x1=1
x2=1
x1=-1
x2=-1
Yes, the answer is correct.
Score: 1
Accepted Answers:
x2=1
x1=-1

16) Given an MP neuron with the inputs as x1,x2,x3,x4,x5 and threshold θ = 3 where 1 point
x5 is inhibitory input. For input (1,1,1,0,1) what will be the value of y?

y = 0

y = 1 since θ ≥ 3

https://onlinecourses.nptel.ac.in/noc24_cs114/unit?unit=17&assessment=280 7/8
10/27/24, 1:12 PM Deep Learning - IIT Ropar - - Unit 4 - Week 1

y = 1/2

Insufficient information

Yes, the answer is correct.

Score: 1
Accepted Answers:
y = 0

17) An MP neuron takes two inputs x1 and x2. Its threshold is θ = 0 . Select all the 1 point
boolean functions this MP neuron may represent.

AND
NOT
OR
NOR

Yes, the answer is correct.

Score: 1
Accepted Answers:
NOR

18) What is the output of a perceptron with weight vector w = [ 2 −3 1 ] and bias 1 point
b = −2 when the input is x = [ 1 0 −1 ] ?

0
1
-1
2

No, the answer is incorrect.

Score: 0
Accepted Answers:
-1

19) What is the ”winter of AI” referring to in the history of artificial intelligence? 1 point

The period during winter when AI technologies are least effective due to cold
temperatures
A phase marked by decreased funding and interest in AI research.
The season when AI algorithms perform at their peak efficiency.
A period characterized by rapid advancements and breakthroughs in AI technologies.

Yes, the answer is correct.

Score: 1
Accepted Answers:
A phase marked by decreased funding and interest in AI research.

https://onlinecourses.nptel.ac.in/noc24_cs114/unit?unit=17&assessment=280 8/8