[go: up one dir, main page]
Scribd
Upload
31 views4 pages

Deep Learning - IIT Ropar - Unit 5 - Week 2

Uploaded by

Mallikarjuna Rao Yamarthy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
31 views4 pages

Deep Learning - IIT Ropar - Unit 5 - Week 2

Uploaded by

Mallikarjuna Rao Yamarthy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

X

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

arjunyamarthy@gmail.com 

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

If already
registered, click
to check your
Week 2 : Assignment
payment status The due date for submitting this assignment has passed.
Due on 2024-02-07, 23:59 IST.

Course Assignment submitted on 2024-02-07, 19:29 IST


outline
1) Which of the following statements about the sigmoid function is NOT true? 1 point

About The derivative of the sigmoid function can be negative.


NPTEL () The sigmoid function is continuous and differentiable.
The sigmoid function maps any input value to a value between 0 and 1.
How does an
NPTEL The sigmoid function can be used as an activation function in neural networks.
online Yes, the answer is correct.
course Score: 1
work? () Accepted Answers:
The derivative of the sigmoid function can be negative.
Week 0 ()
2) How many boolean functions can be designed for 4 inputs? 1 point
Week 1 ()
65,536
Week 2 () 8
256
Linearly
64
Separable
Boolean No, the answer is incorrect.
Functions Score: 0
(unit? Accepted Answers:
unit=36&lesso 65,536
n=37)

Representatio 3) How many neurons do you need in the hidden layer of a perceptron to learn any 1 point
n Power of a boolean function with 4 inputs? (Only one hidden layer is allowed)
Network of
Perceptrons 16
(unit? 64
unit=36&lesso
n=38)
56
32
Sigmoid
Neuron (unit? Yes, the answer is correct.
unit=36&lesso Score: 1
n=39) Accepted Answers:
16
A typical
Supervised 4) We have a function that we want to approximate using 150 rectangles (towers). How 1 point
Machine many neurons are required to construct the required network?
Learning
Setup (unit? 301
unit=36&lesso 451
n=40)
150
Learning 500
Parameters:
(Infeasible) No, the answer is incorrect.
Score: 0
guess work
(unit? Accepted Answers:
unit=36&lesso 301
n=41)
5) What happens to the output of the sigmoid function as |x| becomes very large for 1 point
Learning
input x?Select all relevant operations
Parameters:
Gradient
The output approaches 0.5
Descent (unit?
unit=36&lesso The output approaches 1.
n=42) The output oscillates between 0 and 1.

Representatio The output approaches 0.


n Power of No, the answer is incorrect.
Multilayer Score: 0
Network of Accepted Answers:
Sigmoid The output approaches 1.
Neurons (unit?
The output approaches 0.
unit=36&lesso
n=43)
6) We have a classification problem with labels 0 and 1. We train a logistic model and 1 point
Lecture find out that ω0 learned by our model is -17. We are to predict the label of a new test point x
Material for using this trained model. If ωT x = 1 , which of the following statements is True?
Week 2 (unit?
unit=36&lesso
n=44) We cannot make any prediction as the value of ωT x does not make sense

Week 2 The label of the test point is 0.


Feedback The label of the test point is 1.
Form: Deep
Learning - IIT We cannot make any prediction as we do not know the value of x .
Ropar (unit?
unit=36&lesso Yes, the answer is correct.
Score: 1
n=185)
Accepted Answers:
Week 2: The label of the test point is 0.
Solution (unit?
unit=36&lesso 7) 1 point
n=246)

1
1
Quiz: Week 2 The diagram given below is a section of the sigmoid function given by y = .
: Assignment 1 + e
−(ω 0+ω T x)

(assessment? Which of the following statements is true with respect to the given diagram? (Blue lines denotes
name=264) y = 0.5 line and ωT x = 14 line)

Week 3 ()

week 4 ()

Week 5 ()

Week 6 ()

Week 7 ()

Week 8 ()

Week 9 ()

week 10 ()
ω0 = 14

Week 11 ()
ω0 = −14

Week 12 () ω > 0

ω < 0
Download
Videos () Yes, the answer is correct.
Score: 1
Books () Accepted Answers:
ω0 = −14

Text 8) Suppose we have a function f (x 1 , x 2 ) = x 21 + 3x 2 + 25 which we want to 1 point


Transcripts () minimize the given function using the gradient descent algorithm. We initialize
(x 1 , x 2 ) = (0, 0) . What will bethe value of x 1 after ten updates in the gradient descent

Problem process?(Let η be 1)
Solving
Session - 0
Jan 2024 () -3
−4.5
−3

Yes, the answer is correct.


Score: 1
Accepted Answers:
0

9) Consider a function f (x) = x 3 − 3x 2 + 2. What is the updated value of x after 2nd


iterationof the gradient descent update, if the learning rate is 0.1 and the initial value of x is 4?

1.6

No, the answer is incorrect.

S 0
Score: 0
Accepted Answers:
(Type: Range) 1.76,1.82
1 point

10) What is the purpose of the gradient descent algorithm in machine learning? 1 point

To minimize the loss function


To maximize the loss function
To minimize the output function
To maximize the output function

Yes, the answer is correct.


Score: 1
Accepted Answers:
To minimize the loss function

You might also like