Skip to content
EndsemNov 20232019 patternBE Comp

Deep Learning (DL) SPPU Endsem Question Paper Nov 2023

All 8 questions from this SPPU endsem paper, as printed. Read them here or open the PDF.

Open the PDFMost repeated DL questions
Subject code
410251
Pattern
2019 pattern
Exam
Endsem
Session
Nov 2023
Max. marks
70
Time
2½ Hours
Semester
VIII
Paper code
[6181]-115

Printed for: B.E. (Computer Engineering)

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.
  2. Figures to the right indicate full marks.
  3. Neat diagrams must be drawn wherever necessary.
  4. Make suitable assumption whenever necessary.

Questions

  1. Q1

    1. a)

      Explain stride Convolution with example.

      [6]
    2. b)

      Explain Padding and its types.

      [6]
    3. c)

      Explain Local response normalization and need of it.

      Also asked:May 2025

      [6]

  2. Q2

    1. a)

      Explain ReLU Layer and its advantages.

      Also asked:May 2023

      [6]
    2. b)

      Explain Pooling layers and its types with examples.

      Also asked:May 2025 ·May 2024 ·May 2023

      [6]
    3. c)

      What are the applications of Convolution with examples?

      [6]

  3. Q3

    1. a)

      Draw CNN architecture and explain its working.

      [6]
    2. b)

      Explain the types of Recurrent Neural Network.

      Also asked:May 2025 ·May 2023

      [6]
    3. c)

      Justify RNN is better suited to treat sequential data than a feed forward neural network. 2

      [5]

  4. Q4

    1. a)

      Explain Recurrent Neural Network with its architecture.

      Also asked:May 2025 ·May 2023

      [6]
    2. b)

      Draw and explain architecture for Long Short-Term Memory (LSTM).

      [6]
    3. c)

      Explain how the memory cell in the LSTM is implemented computationally?

      [5]

  5. Q5

    1. a)

      Explain Deep generative model with example.

      Also asked:Nov 2025 ·May 2025 ·May 2024 ·May 2023

      [6]
    2. b)

      How does GAN training scale with batch size?

      [6]
    3. c)

      List the applications of GAN network with description.

      [6]

  6. Q6

    1. a)

      Draw and explain architecture of Boltzmann machine.

      [6]
    2. b)

      Explain different types of GAN.

      Also asked:May 2024

      [6]
    3. c)

      Explain Deep Belief Network with diagram.

      Also asked:Nov 2025 ·May 2025 ·May 2024 ·May 2023

      [6]

  7. Q7

    1. a)

      Explain dynamic programming algorithms for reinforcement learning.

      Also asked:Nov 2024 ·May 2024 ·May 2023

      [6]
    2. b)

      What is deep reinforcement learning? Explain in detail.

      Also asked:May 2025 ·May 2023

      [6]
    3. c)

      Explain Simple reinforcement learning for Tic-Tac-Toe.

      Also asked:Nov 2025 ·May 2025 ·May 2023

      [5]

  8. Q8

    1. a)

      Explain Markov decision process.

      Also asked:Nov 2025 ·May 2025 ·May 2023

      [6]
    2. b)

      Write Short Note on Q Learning and Deep Q-Networks.

      Also asked:May 2023

      [6]
    3. c)

      What are the challenges of reinforcement learning? Explain any four in detail. 

      Also asked:May 2025 ·May 2023

      [5]