[go: up one dir, main page]
Scribd
Upload
6 views1 page

Deep Learning

This document outlines the examination structure for the B. Tech (Sixth Semester Regular) course on Deep Learning at GIET University, including the distribution of marks and types of questions. It consists of two parts: Part A with short answer questions and Part B with detailed questions covering various topics in deep learning such as neural networks, optimization techniques, and applications. The exam is scheduled for May 2024 and has a total of 70 marks.

Uploaded by

CAP
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
6 views1 page

Deep Learning

This document outlines the examination structure for the B. Tech (Sixth Semester Regular) course on Deep Learning at GIET University, including the distribution of marks and types of questions. It consists of two parts: Part A with short answer questions and Part B with detailed questions covering various topics in deep learning such as neural networks, optimization techniques, and applications. The exam is scheduled for May 2024 and has a total of 70 marks.

Uploaded by

CAP
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/ 1

QP Code:RM21BTECH511 Reg.

AY 21
No

GIET UNIVERSITY, GUNUPUR – 765022


B. Tech (Sixth Semester Regular) Examinations, May – 2024
21BCMPE36001 - Deep Learning
(CSE - AIML)
Time: 3 hrs Maximum: 70 Marks
(The figures in the right hand margin indicate marks)
PART – A (2 x 5 = 10 Marks)

Q.1. Answer ALL questions CO # Blooms


Level
a. What is K-fold cross validation? CO1 K1
b. What are the applications of Long Short Term Memory? CO3 K1
c. Differentiate between encoder and decoder. CO4 K2
d. What are the different types of RNN topologies? CO1 K1
e. Define Adam Optimizer. CO2 K2

PART – B (15 x 4=60 Marks)

Answer ALL questions Marks CO # Blooms


Level

2. a. What are the different challenges faced by deep neural networks? Explain its types. 8 CO2 K2

b. Explain the key operation of linear algebra used for deep learning with example. 7 CO1 K1

(OR)
c. What is Recurrent Neural Network (RNN)? Write its applications and what are the 8 CO3 K1
challenges in training RNN.
d. Compare Supervised, Unsupervised and Semi Supervised learning. 7 CO1 K1

3.a. What is Convolution Neural Network? Explain pooling , padding and convolution 8 CO3 K1
operation with the help of examples
b. Compare machine learning and deep learning. Explain the few real time applications 7 CO1 K2
of deep learning.

(OR)
c. Explain the importance of Greedy layer wise pre training in deep neural network. 7 CO2 K2

d. Explain the dimensionality reduction and classification principles used in auto 8 CO4 K1
encoder.
4.a. Write a short note on Tensor flow library. 8 CO1 K1

b. What is Long Short Term Memory (LSTM)? Explain its architecture and working 7 CO3 K2
mechanism.
(OR)
c. Why optimization is required in deep neural network? Compare the working 8 CO2 K2
mechanism of Adam and Adagrad optimizers.
d. Differentiate between Under complete and De- noising auto encoder. 7 CO4 K2

5.a. What is activation function? Explain in detail regarding different type of activation 7 CO2 K2
function used in deep neural network.

b. Write Short Notes on: (i) Image Net (ii) VGG Net 8 CO3 K1

(OR)
c. Discuss the importance of Dimensionality reduction and Cross validation in deep 8 CO1 K1
learning. Explain K- Fold Cross validation.
d. Explain the applications of auto encoder in image dimensionality reduction. 7 CO2 K2

--- End of Paper ---

Page 1 of 1

You might also like