Skip to content
EndsemNov 20252019 patternBE IT

Deep Learning (DL) SPPU Endsem Question Paper Nov 2025

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 2025
Max. marks
70
Time
2½ Hours
Semester
VII
Paper code
[6584]-175

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. Assume suitable data, if necessary.
  3. Neat diagrams must be drawn wherever necessary.
  4. Figures to the right indicate full marks.

Questions

  1. Q1

    1. a)

      What type of neural network is preferred for sequence modeling? Why? State other applications with architectural diagrams for this type of neural network.

      [9]
    2. b)

      How RNN is different than simple neural network? Draw architecture diagram and explain functioning.

      [9]

  2. Q2

    1. a)

      What type of neural network is preferred for hierarchical data analysis? Why? State other applications with architectural diagrams for this type of neural network.

      [9]
    2. b)

      Differentiate among RvNN, RNN and FFNN.

      [9]

  3. Q3

    1. a)

      What is encoder-decoder architecture pattern? Where is it used?

      [8]
    2. b)

      What is a regularized auto-encoder? Where is it used?

      Also asked:May 2025

      [9]

  4. Q4

    1. a)

      Write a short note on - Applications of autoencoders.

      [8]
    2. b)

      Differentiate among contractive autoencoders and Stochastic autoencoders.

      [9]

  5. Q5

    1. a)

      What are the variants of CNN? Explain any one in detail.

      [9]
    2. b)

      Explain the concept of domain adaptation with suitable examples. 2

      [9]

  6. Q6

    1. a)

      Explain the concept of distributed presentation with suitable examples.

      [9]
    2. b)

      What is greedy layer-wise pre-training network?

      Also asked:May 2025 ·Nov 2023

      [9]

  7. Q7

    1. a)

      How are deep learning techniques used in NLP systems? Explain with diagrams.

      [8]
    2. b)

      Explain deep learning-based recommender systems with suitable diagrams.

      Also asked:May 2025 ·May 2023

      [9]

  8. Q8

    1. a)

      Explain the role of CNNs in computer vision.

      [8]
    2. b)

      How is social network analysis done using deep learning architectures? 

      Also asked:May 2025 ·May 2023

      [9]