Skip to content
EndsemMay 20232019 patternBE IT

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
414443
Pattern
2019 pattern
Exam
Endsem
Session
May 2023
Max. marks
70
Time
2½ Hours
Semester
VII
Paper code
[6004]-565

Printed for: B.E.(InformationTechnology)

Instructions to the candidates

  1. Answer Q1 or Q2, Q3 or Q4, Q5 or Q6, Q7 or Q8.
  2. Neat diagrams must be drawn wherever necessary.
  3. Figures to the right indicate full marks.
  4. Assume suitable data, if necessary.

Questions

  1. Q1

    1. a)

      Differentiate between Recurrent Neural Network and Recursive Neural Network with appropriate diagram.

      [9]
    2. b)

      Explain the general layout of a Long Short-Term Memory Network (LSTM) with suitable diagram.

      Also asked:May 2024 ·Nov 2023 ·Nov 2022

      [9]

  2. Q2

    1. a)

      Explain how sequence to sequence model works.

      Also asked:May 2024 ·Nov 2022

      [9]
    2. b)

      Describe Recursive Neural Network and types of Recursive Neural Network. Explain its advantages.

      [9]

  3. Q3

    1. a)

      Explain the architecture of sparse autoencoder with suitable diagram. What are advantages of sparse encoder over usual autoencoder?

      [9]
    2. b)

      State applications of autoencoder. Explain any two applications in detail.

      [8]

  4. Q4

    1. a)

      Explain the structure of regularized autoencoders. What is the purpose of sparsity constraint in sparse autoencoder?

      [9]
    2. b)

      Explain architecture of autoencoder with neat diagram. Explain the hyperparameters that must be set before training of autoencoders. 2

      [8]

  5. Q5

    1. a)

      When will you transfer learning? Explain with example.

      [9]
    2. b)

      Explain architecture of DenseNet.

      [9]

  6. Q6

    1. a)

      Why is the network called Greedy Layer Wise Pretraining Network?

      Also asked:Nov 2022

      [9]
    2. b)

      Write Short note on i) Representation Learning ii) Distributed Representation.

      [9]

  7. Q7

    1. a)

      Explain CNN based and RNN based framework for natural language processing.

      [9]
    2. b)

      Describe deep learning based recommender systems with suitable diagram.

      Also asked:Nov 2025 ·May 2025

      [8]

  8. Q8

    1. a)

      Illustrate the social network analysis using deep learning and enlist the applications of social network analysis.

      Also asked:Nov 2025 ·May 2025

      [9]
    2. b)

      What are the application areas of image classification? Explain CNN for image Classification. 

      Also asked:Nov 2022

      [8]