Scribd
Upload
24 views2 pages

Deep Learning 23

This document outlines the examination details for the B. Tech course in Deep Learning at Dr. Babasaheb Ambedkar Technological University for the Summer Examination 2023. It includes instructions for students, a breakdown of questions with marks, and topics covering various aspects of artificial neural networks, convolutional neural networks, transfer learning, recurrent neural networks, and applications of deep learning. The exam consists of multiple questions that require students to demonstrate their understanding of these concepts.

Uploaded by

Raj Adsul
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
24 views2 pages

Deep Learning 23

This document outlines the examination details for the B. Tech course in Deep Learning at Dr. Babasaheb Ambedkar Technological University for the Summer Examination 2023. It includes instructions for students, a breakdown of questions with marks, and topics covering various aspects of artificial neural networks, convolutional neural networks, transfer learning, recurrent neural networks, and applications of deep learning. The exam consists of multiple questions that require students to demonstrate their understanding of these concepts.

Uploaded by

Raj Adsul
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/ 2

DR.

BABASAHEB AMBEDKAR TECHNOLOG


ICAL UNIVERSITY, LONERE
Summer Examination - 2023
Course: B. Tech. Branch: CSE(AI&ML) Semester: VI

Subject Code & Name: BTAIC601 / Deep Learning


Max Marks: 60 Date: Duration: 3 Hr.
Instructions to the Students:
1. All the questions are compulsory.
2. The level of question/expected answer as per OBE or the Course Outcome (CO) on
which the question is based is mentioned in front of the question.
3. Use of non-programmable scientific calculators is allowed.
4. Assume suitable data wherever necessary and mention it clearly.
(Level/CO) Marks

Q. 1 Solve Any Two of the following. 12

A) Differentiate between Artificial Neural Network and Biological Neural (L4/CO1) 6

Network.

B) Explain perceptron learning for ANN. (L1/CO1) 6

C) Compare and contrast linearly separable and linearly non separable (L2/CO1) 6

problems with suitable example.

12
Q.2 Solve Any Two of the following.

A) Describe the architecture of Convolutional Neural Network. (L1/CO2) 6

B) In CNN what are the pros and cons of using max pooling layer Vs. Average (L2/CO2) 6

pooling layer.
(L5/CO2) 6
C) Enlist and justify advantages of using Convolutional Neural
the Network

Vs. Dense Neural Network for image classification.

12
Q.3 Solve Any Two of the following.
? Explain them in brief. (L1/CO3) 6
A) What are the different ways of transfer learning
(L1/CO3) 6
B) Explain back propagation learning algorithm in detail.
6
for handling overfitting issues during deeр (L2/CO3)
C) Discuss the different techniques

learning process.

12

Q.4 Solve Any Two of the following.


6
(L1/CO4)
Recurrent Neural Networ
k (RNN)?
A) What is a 6
overcome this
(L2/CO4)
is "Dead Neuron Proble
m"? How can Leaky ReLU
B) What

problem? (L2/CO4) 6
ng Mc Culloch Pitts
in detail the imp lementation of AND gate usi
C) Discuss
neuron model.
.5 Solve Any Two of the follow
ing. 12
A) Explain and enlist the applications of Neural Style Transfer. - (L1/CO5) 6

B) How image denoising is achieved using Deep Learning techniques. (L4/CO5) 6

6
Cr Write Short note on Generative Adversarial Network. (L2/CO5)

*** End ***

be hidden before final printing.


The grid and the borders of the table will

You might also like