Skip to content
EndsemNov 20222019 patternBE IT

Deep Learning (DL) SPPU Endsem Question Paper Nov 2022

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
Nov 2022
Max. marks
70
Time
2½ Hours
Semester
VII
Paper code
[5927]-393

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 indicate full marks.
  4. Assume suitable data, if necessary.

Questions

  1. Q1

    1. a)

      Differentiate between feed-forward neural networks and recurrent neural networks. Explain the types of Recurrent Neural Network (RNN).

      Also asked:Nov 2024 ·May 2024 ·Nov 2023

      [9]
    2. b)

      Explain how sequence to sequence model works.

      Also asked:May 2024 ·May 2023

      [9]

  2. Q2

    1. a)

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

      Also asked:May 2024 ·Nov 2023 ·May 2023

      [9]
    2. b)

      What is Recurrent Neural Network (RNN)? State and explain types of RNN in brief.

      Also asked:Nov 2024 ·May 2024 ·Nov 2023

      [9]

  3. Q3

    1. a)

      Autoencoders use unsupervised learning approach. Justify the statement.

      [9]
    2. b)

      Explain the concept of contractive autoencoder and its need.

      [8]

  4. Q4

    1. a)

      State the applications of Autoencoders. Explain how the dimensionality reduction feature of autoencoder is useful in information retrieval task?

      [9]
    2. b)

      Explain denoising autoencoders with suitable figure.

      [8]

  5. Q5

    1. a)

      Why is the network called Greedy Layer Wise Pretraining Network?

      Also asked:May 2023

      [9]
    2. b)

      State and Justify Role of Representation Learning. 2

      [9]

  6. Q6

    1. a)

      Explain distributed representation with example.

      [9]
    2. b)

      Justify when to use domain adaptation and when to use transfer learning.

      Also asked:Nov 2023

      [9]

  7. Q7

    1. a)

      Explain graph convolution approach for social network analysis? Describe RNN based framework for NLP. Write any four applications of NLP.

      [9]
    2. b)

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

      Also asked:May 2023

      [8]

  8. Q8

    1. a)

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

      Also asked:Nov 2024 ·May 2024

      [9]
    2. b)

      Explain basic architecture of Automatic Speech Recognition system. Why RNN is suitable for speech recognition? How bidirectional RNNs are used in automatic speech recognition?  

      [8]