Scribd
Upload
61 views2 pages

CST414 QP

This document is an examination paper for the Sixth Semester B.Tech Degree in Deep Learning at APJ Abdul Kalam Technological University, covering various topics in neural networks. It consists of two parts: Part A includes short answer questions worth 3 marks each, while Part B contains detailed questions from different modules worth 14 marks each. The exam assesses knowledge on multilayer perceptrons, overfitting, convolutional neural networks, and other deep learning concepts.

Uploaded by

sonyajimon306
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
61 views2 pages

CST414 QP

This document is an examination paper for the Sixth Semester B.Tech Degree in Deep Learning at APJ Abdul Kalam Technological University, covering various topics in neural networks. It consists of two parts: Part A includes short answer questions worth 3 marks each, while Part B contains detailed questions from different modules worth 14 marks each. The exam assesses knowledge on multilayer perceptrons, overfitting, convolutional neural networks, and other deep learning concepts.

Uploaded by

sonyajimon306
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

B 0400CST414052302 Pages: 2

Reg No.:_______________ Name:__________________________


APJ ABDUL KALAM TECHNOLOGICAL UNIVERSITY
Sixth Semester B.Tech Degree (PT) (R) Examination June 2023 (2019 Scheme)

Course Code: CST414


Course Name: DEEP LEARNING
Max. Marks: 100 Duration: 3 Hours

PART A
Answer all questions, each carries 3 marks. Marks

1 Discuss the advantages of multilayer perceptrons with an example. (3)


2 Define overfitting. List any two solutions to solve overfitting problem in neural (3)
network.
3 Discuss need of parameter initialization and early stopping. (3)
4 Explain any two ensemble methods. (3)
5 Identify the datatypes that can be handled by Convolutional Neural Networks. (3)
6 List any two pooling methods with example. (3)
7 What kind of data can be handled by Recurrent Neural Network. Explain. (3)
8 List any three applications of LSTM. (3)
9 Explain boltzmann machines in deep learning. (3)
10 Explain computer vision implementation with deep learning concepts. (3)
PART B
Answer any one full question from each module, each carries 14 marks.
Module I
11 a) Explain all practical challenges and solutions in neural network training. (14)
OR
12 a) Implement the back propagation algorithm to train Multi Layer Perceptron using (14)
sigmoid activation function.
Module II
13 a) Compare different parameter specific learning and momentum based learning (14)
strategies in gradient descent optimization.
OR
14 a) Sketch diagram of Convolutional Neural Network Architecture and explain (14)
functionalities of different layers using simple example.

Page 1of 2
0400CST414052302

Module III
15 a) Demonstrate motivation behind convolution neural network incorporating (14)
different diagrams.
OR
16 a) Demonstrate convolution operation on 7x7 colour image to extract horizontal and (7)
vertical edges with an example.
b) Write the input volume, filter and output volume characteristics in convolution (7)
layer with an example.
Module IV
17 a) Sketch diagrams of Recursive Neural Network and Long Short Term Memory. (14)
Compare the working of RNN and LSTM.
OR
18 a) Explain the process of unfolding RNN into computational graph with an example. (8)
b) Sketch the diagram of sequence to sequence architecture, explain it’s working (6)
with an example.
Module V
19 a) Explain three word embedding techniques. (7)

b) Explain the merits and demerits of different types of Autoencoders. (7)


OR
20 a) Explain natural language processing. (7)
b) Explain designing of Speech Recognition system. (7)
****

Page 2of 2

You might also like