10/27/24, 1:13 PM Deep Learning - IIT Ropar - - Unit 5 - Week 2

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

[email protected] 

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

Course Week 2 : Assignment 2

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, 17:34 IST
How does an 1) How many boolean functions can be designed for 3 inputs? 1 point
NPTEL
online 8
course 16
work? ()
256

Week 1 () 64
Yes, the answer is correct.
Week 2 () Score: 1
Accepted Answers:
Linearly 256
Separable
Boolean 2) Which of the following statements is(are) true about the following function? 1 point
Functions 1
σ(z) =
(unit? 1+e
−(z)

unit=36&lesso
The function is bounded between 0 and 1
n=37)

Representatio The function attains its maximum when z → ∞

n Power of a
The function is continuously differentiable
Network of
Perceptrons The function is monotonic
(unit? Yes, the answer is correct.
unit=36&lesso Score: 1
n=38) Accepted Answers:
The function is bounded between 0 and 1
Sigmoid
Neuron (unit?
The function attains its maximum when z → ∞

The function is continuously differentiable

The function is monotonic

https://onlinecourses.nptel.ac.in/noc24_cs114/unit?unit=36&assessment=281 1/4
10/27/24, 1:13 PM Deep Learning - IIT Ropar - - Unit 5 - Week 2

unit=36&lesso
n=39)
3) How many weights does a neural network have if it consists of an input layer with 2
neurons, three hidden layers each with 4 neurons, and an output layer with 2 neurons? Assume
Learning there are no bias terms in the network.
Parameters:
(Infeasible) 48
guess work
(unit? Yes, the answer is correct.
Score: 1
unit=36&lesso
n=41) Accepted Answers:
(Type: Numeric) 48
Learning
Parameters: 1 point
Gradient
4) You are training a model using the gradient descent algorithm and notice that the 1 point
Descent (unit?
loss decreases and then increases after each successive epoch (pass through the data). Which
unit=36&lesso
n=42) of the following techniques would you employ to enhance the likelihood of the gradient descent
algorithm converging? (Here, η refers to the step size.)
Representatio
n Power of
Multilayer Decrease the value of η
Network of
Sigmoid Increase the value of η
Neurons (unit?
unit=36&lesso Set η = 1
n=43)
Set η = 0
Lecture
Material for Yes, the answer is correct.
Week 2 (unit? Score: 1
unit=36&lesso Accepted Answers:
n=44) Decrease the value of η

Quiz: Week 2
: Assignment
5) Which of the following statements is true about the representation power of a 1 point
2 multilayer network of perceptions?
(assessment?
name=281)
A multilayer network of perceptrons can represent any function.
A multilayer network of perceptrons can represent any linear function.
Week 2
Feedback A multilayer network of perceptrons can represent any boolean function.
Form: Deep A multilayer network of perceptrons can represent any continuous function.
Learning - IIT
Yes, the answer is correct.
Ropar (unit?
Score: 1
unit=36&lesso
Accepted Answers:
n=185)
A multilayer network of perceptrons can represent any boolean function.
Week 3 ()
6) How many boolean functions can be designed for 4 inputs? 1 point
week 4 ()
65,536

Week 5 () 8
256
Week 6 () 64

Yes, the answer is correct.

Week 7 () Score: 1
Accepted Answers:
65,536

https://onlinecourses.nptel.ac.in/noc24_cs114/unit?unit=36&assessment=281 2/4
10/27/24, 1:13 PM Deep Learning - IIT Ropar - - Unit 5 - Week 2

Week 8 () 7) What happens to the output of the sigmoid function as |x| becomes very large for 1 point
input x?Select all relevant operations
Week 9 ()
The output approaches 0.5
week 10 () The output approaches 1.
The output oscillates between 0 and 1.
Week 11 ()
The output approaches 0.

Week 12 () Yes, the answer is correct.

Score: 1
Accepted Answers:
Download The output approaches 1.
Videos ()
The output approaches 0.

Books ()
8) We have a classification problem with labels 0 and 1. We train a logistic model and 1 point
find out that ω0 learned by our model is -17. We are to predict the label of a new test point x
Text
using this trained model. If ωT x = 1 , which of the following statements is True?
Transcripts
()
We cannot make any prediction as the value of ωT x does not make sense
Problem The label of the test point is 0.
Solving
The label of the test point is 1.
Session -
July 2024 ()
We cannot make any prediction as we do not know the value of x .

Yes, the answer is correct.

Score: 1
Accepted Answers:
The label of the test point is 0.

9) The diagram given below is a section of the sigmoid function given by 1 point
1
y =
T
. Which of the following statements is true with respect to the given
−(ω 0+ω x)
1 + e

diagram? (Blue lines denotes y = 0.5 line and ωT x = 14 line)

ω0 = 14

ω0 = −14

https://onlinecourses.nptel.ac.in/noc24_cs114/unit?unit=36&assessment=281 3/4
10/27/24, 1:13 PM Deep Learning - IIT Ropar - - Unit 5 - Week 2

ω > 0

ω < 0

No, the answer is incorrect.

Score: 0
Accepted Answers:
ω0 = −14

10) Suppose we have a function f (x 1 , x 2 ) 1

+ 3x 2 + 25 which we want to
= x
2
1 point
minimize the given function using the gradient descent algorithm. We initialize
(x 1 , x 2 ) = (0, 0) . What will be the value of x 1 after ten updates in the gradient descent
process?(Let η be 1)

0
-3
−4.5
−3

Yes, the answer is correct.

Score: 1
Accepted Answers:
0

https://onlinecourses.nptel.ac.in/noc24_cs114/unit?unit=36&assessment=281 4/4