Skip to content
EndsemMay 20242019 patternBE IT

Deep Learning (DL) SPPU Endsem Question Paper May 2024

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
414443
Pattern
2019 pattern
Exam
Endsem
Session
May 2024
Max. marks
70
Time
2½ Hours
Semester
VII
Paper code
[6263]-172

Printed for: B.E. (Information Technology)

Instructions to the candidates

  1. Answer Q.1 or Q.2, Q.3 or Q.4, Q.5 or Q.6, Q.7 or Q.8.
  2. Neat diagrams must be drawn wherever necessary.
  3. Figures to the right side indicate full marks.
  4. Assume suitable data, if necessary.

Questions

  1. Q1

    1. a)

      Write a short note on Long Short-Term Memory Networks (LSTM).

      Also asked:Nov 2023 ·May 2023 ·Nov 2022

      [9]
    2. b)

      Explain how sequence to sequence model works.

      Also asked:May 2023 ·Nov 2022

      [9]

  2. Q2

    1. a)

      Differentiate between Feed-Forward Neural Networks Vs Recurrent Neural Networks. Explain the types of Recurrent Neural Network (RNN).

      Also asked:Nov 2024 ·Nov 2023 ·Nov 2022

      [9]
    2. b)

      Explain the components of a Long Short-Term Memory Networks (LSTM) and Advantages of LSTM.

      Also asked:Nov 2023 ·May 2023 ·Nov 2022

      [9]

  3. Q3

    1. a)

      Explain the architecture of undercomplete autoencoder. What is the difference between undercomplete autoencoder and sparse autoencoder?

      Also asked:Nov 2024

      [9]
    2. b)

      What are Denoising Autoencoders. Why it is used?

      [8]

  4. Q4

    1. a)

      How do Autoencoders work? What are the applications of autoencoder?

      [9]
    2. b)

      What is a Bottleneck in autoencoder and why is it used? 2

      [8]

  5. Q5

    1. a)

      What is greedy layerwise pretraining? Explain the approaches.

      [9]
    2. b)

      Why should one use transfer learning and when?

      [9]

  6. Q6

    1. a)

      When Vanishing Gradient Problem Occurs? Explain in detail

      [9]
    2. b)

      Explain distributed representation with example.

      [9]

  7. Q7

    1. a)

      Explain the traditional approach and deep learning approach for Automatic Speech Recognition.

      [8]
    2. b)

      Explain content based, collaborative and hybrid recommender system with pros and cons.

      Also asked:Nov 2024 ·Nov 2022

      [9]

  8. Q8

    1. a)

      Explain the following social network analysis terminologies i) Nodes & Ages ii) Weight iii) Centrality Measures iv) Network Level Measures

      [8]
    2. b)

      This part has equations that don’t show as text. Open the PDF to read it.

      [9]