0% found this document useful (0 votes)
32 views2 pages

DL Dec - 2023

The document is an exam paper containing 8 questions related to deep learning topics. It covers concepts like convolutional neural networks, recurrent neural networks, generative adversarial networks, reinforcement learning, and more. Students are required to answer 4-5 questions from the list in detail within the allotted time frame.

Uploaded by

Shubham
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
0% found this document useful (0 votes)
32 views2 pages

DL Dec - 2023

The document is an exam paper containing 8 questions related to deep learning topics. It covers concepts like convolutional neural networks, recurrent neural networks, generative adversarial networks, reinforcement learning, and more. Students are required to answer 4-5 questions from the list in detail within the allotted time frame.

Uploaded by

Shubham
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

Total No. of Questions : 8] SEAT No.

8
23
P6565 [Total No. of Pages : 2

ic-
[6181]-115

tat
B.E. (Computer Engineering)

1s
DEEP LEARNING

7:3
(2019 Pattern) (Semester - VIII) (410251)

02 91
3:3
Time : 2½ Hours] [Max. Marks : 70

0
31
1/1 13
Instructions to the candidates:
1) Solve Q.1 or Q.2, Q.3 or Q.4, Q.5 or Q.6, Q.7 or Q.8.
0
2) Figures to the right indicate full marks.
2/2
.23 GP

3) Neat diagrams must be drawn wherever necessary.


4) Make suitable assumption whenever necessary.
E
80

8
C

23
ic-
16

tat
8.2

1s
Q1) a) Explain stride Convolution with example. [6]
.24

7:3
91
49

3:3
b) Explain Padding and its types. [6]
30
31

c) Explain Local response normalization and need of it. [6]


01
02
2/2
GP

OR
1/1
CE

Q2) a) Explain ReLU Layer and its advantages. [6]


80

8
23
.23

b) Explain Pooling layers and its types with examples. [6]


ic-
16

tat
8.2

c) What are the applications of Convolution with examples? [6]


1s
.24

7:3
91
49

3:3

Q3) a) Draw CNN architecture and explain its working. [6]


30
31

b) Explain the types of Recurrent Neural Network. [6]


01
02
2/2
GP

c) Justify RNN is better suited to treat sequential data than a feed forward
1/1

neural network. [5]


CE
80

OR
.23
16
8.2
.24

P.T.O.
49

[6181]-115 1
8
Q4) a) Explain Recurrent Neural Network with its architecture. [6]

23
ic-
b) Draw and explain architecture for Long Short-Term Memory (LSTM).[6]

tat
c) Explain how the memory cell in the LSTM is implemented computationally?

1s
[5]

7:3
02 91
3:3
Q5) a) Explain Deep generative model with example. [6]

0
31
b) How does GAN training scale with batch size?
1/1 13 [6]
c) List the applications of GAN network with description. [6]
0
2/2
.23 GP
E
80

OR

8
C

23
Q6) a) Draw and explain architecture of Boltzmann machine. [6]

ic-
16

tat
b) Explain different types of GAN. [6]
8.2

1s
c) Explain Deep Belief Network with diagram. [6]
.24

7:3
91
49

3:3
30
31

Q7) a) Explain dynamic programming algorithms for reinforcement learning.[6]


01
02

b) What is deep reinforcement learning? Explain in detail. [6]


2/2
GP

c) Explain Simple reinforcement learning for Tic-Tac-Toe. [5]


1/1
CE
80

8
23
.23

ic-
OR
16

tat
Q8) a) Explain Markov decision process. [6]
8.2

1s
.24

b) Write Short Note on Q Learning and Deep Q-Networks. [6]


7:3
91
49

3:3

c) What are the challenges of reinforcement learning? Explain any four in


30

detail. [5]
31
01
02
2/2


GP
1/1
CE
80
.23
16
8.2
.24
49

[6181]-115 2

You might also like