Skip to content
EndsemMay 20232019 patternBE Comp

Deep Learning (DL) SPPU Endsem Question Paper May 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
May 2023
Max. marks
70
Time
2½ Hours
Semester
VIII
Paper code
[6004]-494

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.7or Q.8
  2. Figures to the right indicate full marks.
  3. Neat diagrams must be drawn whenever necessary.
  4. Make suitable assumption whenever necessary.

Questions

  1. Q1

    1. a)

      Explain Pooling Layer with its need and different types.

      Also asked:May 2025 ·May 2024 ·Nov 2023

      [6]
    2. b)

      Draw and explain CNN (Convolution Neural Network) architecture in detail.

      Also asked:Mar 2025

      [6]
    3. c)

      Explain ReLU Layer in detail. What are the advantages of ReLU over Sigmoid?

      Also asked:Nov 2023

      [6]

  2. Q2

    1. a)

      Explain all the features of pooling layer.

      Also asked:May 2025

      [6]
    2. b)

      Explain Dropout Layer in Convolutional Neural Network.

      Also asked:May 2024

      [6]
    3. c)

      Explain working of Convolution Layer with its features.

      Also asked:May 2025

      [6]

  3. Q3

    1. a)

      What is RNN? What is need of RNN? Explain in brief about working of RNN (Recurrent Neural Network).

      [6]
    2. b)

      How LSTM and Bidirectional LSTM works.

      [6]
    3. c)

      Explain Unfolding computational graphs with example. 2

      [5]

  4. Q4

    1. a)

      What are types of RNN (Recurrent Neural Network)? How to train RNN explain in brief.

      Also asked:May 2025 ·Nov 2023

      [6]
    2. b)

      Explain Encoder-Decoder Sequence to Sequence architecture with its application.

      Also asked:May 2024

      [6]
    3. c)

      Differentiate between Recurrent and Recursive Neural Network.

      Also asked:May 2025 ·Nov 2023

      [5]

  5. Q5

    1. a)

      Explain Boltzmann machine in details.

      [6]
    2. b)

      Explain GAN (Generative Adversarial Network) architecture with an example.

      Also asked:Nov 2024

      [6]
    3. c)

      Do GANs (Generative Adversarial Network) find real or fake images? If yes explain it in detail.

      [6]

  6. Q6

    1. a)

      Differentiate generative and discriminative models in GAN (Generative Adversarial Network).

      [6]
    2. b)

      What are applications of GAN (Generative Adversarial Network)? Explain any four in detail.

      [6]
    3. c)

      Write Short Note on Deep generative model and Deep Belief Networks.

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

      [6]

  7. Q7

    1. a)

      Explain Markov Decision Process with Markov property.

      Also asked:Nov 2025 ·May 2025 ·Nov 2023

      [6]
    2. b)

      Explain in detail Dynamic programming algorithms for reinforcement learning.

      Also asked:Nov 2024 ·May 2024 ·Nov 2023

      [6]
    3. c)

      Explain Simple reinforcement learning for Tic-Tac-Toe.

      Also asked:Nov 2025 ·May 2025 ·Nov 2023

      [5]

  8. Q8

    1. a)

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

      Also asked:Nov 2023

      [6]
    2. b)

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

      Also asked:May 2025 ·Nov 2023

      [6]
    3. c)

      What is deep reinforcement learning? Explain in detail. 

      Also asked:May 2025 ·Nov 2023

      [5]