NPTEL Deep Learning Assignment 3 Answers 2022

NPTEL Deep Learning Assignment 3

Are you looking for the Answers to NPTEL Deep Learning Assignment 3? This article will help you with the answer to the National Programme on Technology Enhanced Learning (NPTEL) Course “ NPTEL Deep Learning Assignment 3

What is Deep Learning?

The objective of the course is to impart the knowledge and understanding of causes and effects of air pollution and their controlling mechanisms. The course will provide a deeper understanding of air pollutants, pollution inventory and modelling. The course also imparts knowledge on the impacts of air pollution on different aspects such as policy, human health and various contemporary technological innovation for betterment of air quality.


Average assignment score = 25% of the average of best 8 assignments out of the total 12 assignments given in the course.
Exam score = 75% of the proctored certification exam score out of 100

Final score = Average assignment score + Exam score

YOU WILL BE ELIGIBLE FOR A CERTIFICATE ONLY IF THE AVERAGE ASSIGNMENT SCORE >=10/25 AND EXAM SCORE >= 30/75. If one of the 2 criteria is not met, you will not get the certificate even if the Final score >= 40/100.

Below you can find the answers for NPTEL Deep Learning Assignment 3

NPTEL Deep Learning Assignment 3 Answers:-

Q1. Let the input to the Feed Forward Neural network be a 6-dimensional vector and the first hidden layer has 6 neurons. What is the dimension of the W1, weight connecting input layer and the first hidden layer?

Answer:- a

Q2. The Pre-activation at layer i,ai can be best described as

Answer:- b

Q3. Which of the following is True for the activation at layer i given by hi=g(ai(x))?
i. g() is applied to every element in the vector
ii. g() can be a logistic function
iii. g() cannot be a tanh function

Answer:- a

Q4. Given that the output y is a probability distribution, Sigmoid function cannot be used as an output function. Why?

Answer:- a

???? Next Week Answers: Assignment 04 ????

quizxp telegram

Q5. Given that the output is a probability distribution, identify the statements that are True.
i Activation function is softmax
ii Activation function is Linear
iii Loss function if Squared error
iv Loss function is entropy

Answer:- b

Q6. For all the layers from input to the last hidden layer during forward propagation, the activation function is computed as follows:
ak=bk+Wkhk−1. What is h0 to compute a1?

Answer:- c

Q7. Consider the output classes for a random variable X to be Parrot, Dove, Cuckoo and Owl. Some images are given and you have to classify them in one of the four classes. For example, if the actual image is of Owl, the output will be [0,0,0,1]. Identify the best activation function to minimize the loss.

Answer:- a

Q8. Pick out the statement that is True for an event with high probability.

Answer:- b

Q9. Consider a Feed Forward Neural network with x-dimensional vector and the first hidden layer has x neurons. What is the dimension of the B1, bias between the input layer and the first hidden layer?

Answer:- c

Q10. In a Feed Forward Neural network, the hidden layer connected to the output layer has p neurons and the output layer has q neurons each corresponding to one output class. Comment on the dimension of the weight connecting both layers.

Answer:- c

For other courses answers:- Visit

For Internship and job updates:- Visit

Disclaimer: We do not claim 100% surety of answers, these answers are based on our sole knowledge, and by posting these answers we are just trying to help students, so we urge do your assignment on your own.

if you have any suggestions then comment below or contact us at [email protected]

If you found this article Interesting and helpful, don’t forget to share it with your friends to get this information.