Total No. of Questions : 8] SEAT No.

8
23
PB2257 [Total No. of Pages : 2

ic-
[6263]-95

tat
B.E. (Computer Engineering)

5s
DEEP LEARNING

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

02 91
3:2
Time : 2½ Hours] [Max. Marks : 70

0
41
1/0 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.
5/2
.23 GP

3) Neat diagrams must be drawn whenever necessary.

4) Make suitable assumption whenever necessary.
E
81

8
C

23
ic-
Q1) a) Explain CNN architecture with its application. [6]
16

tat
b) What is Padding? Enlist and explain types of padding. [6]
8.2

5s
c) Explain Dropout Layer in Convolutional Neural Network. [6]
.24

7:3
91
OR
49

3:2
Q2) a) Define ReLU. Explain disadvantages of ReLU. [6]
30
41

b) What is Strides in CNN? Explain in brief. [6]

01
02

c) Explain Pooling Layer with its different types. [6]

5/2
GP
1/0

Q3) a) Explain RNN with its types. [6]

CE
81

8
23
b) Explain in brief Encoder Decoder architecture. [6]
.23

ic-
16

c) Explain Different types of Deep Learning. [5]

tat
8.2

5s

OR
.24

7:3

Q4) a) WSN on Performance Matrices. [6]

91
49

3:2

b) Compare implicit and explicit memory. [6]

30
41

c) What are default baseline models? Explain in brief. [5]

01
02
5/2
GP

Q5) a) State and explain different types of GAN. [6]

1/0

b) What is Boltzmann machine? Explain its objectives. [6]

CE
81

c) Write short Note on Deep generative model and Deep Belief Networks.
.23

[6]
16

OR
8.2
.24

P.T.O.
49

[6263]-95 1
Q6) a) Define Boltzmann machine? State and Explain its types. [6]

8
23
b) Explain Discriminator network. [6]

ic-
c) Enlist and Explain applications of GAN. [6]

tat
5s
7:3
02 91
Q7) a) What is Reinforcement Learning? State and explain its advantages and

3:2
disadvantages. [6]

0
41
b) 1/0 13
What are different types of Reinforcement Learning? Explain in brief.[6]
c) Compare Active and Passive Reinforcement Learning. [5]
0
5/2
.23 GP

OR
E
81

8
Q8) a) Write short note on Deep Q-Learning. [6]
C

23
b) What are different characteristics of Reinforcement Learning? [6]

ic-
16

c) Explain in detail Dynamic programming algorithms for reinforcement

tat
8.2

learning. [5]

5s
.24

7:3
91
  
49

3:2
30
41
01
02
5/2
GP
1/0
CE
81

8
23
.23

ic-
16

tat
8.2

5s
.24

7:3
91
49

3:2
30
41
01
02
5/2
GP
1/0
CE
81
.23
16
8.2
.24
49

[6263]-95 2