Skip to content
EndsemNov 20232019 patternBE IT

Deep Learning (DL) SPPU Endsem Question Paper Nov 2023

All 8 questions from this SPPU endsem paper, as printed. Read them here or open the PDF.

Subject code
414443
Pattern
2019 pattern
Exam
Endsem
Session
Nov 2023
Max. marks
70
Time
2½ Hours
Semester
VII
Paper code
[6181]-193

Printed for: B.E. (Information Technology)

Instructions to the candidates

  1. Answer 1/2,3/4, 5/6, 7/8 questions.
  2. Assume Suitable data jf necessary.
  3. Neat diagrams must be drawn wherever necessary.
  4. Figures to the right side indicate full marks.

Questions

  1. Q1

    1. a)

      Discuss Feed-Forward Neural Networks vs Recurrent Neural Networks.

      Also asked:Nov 2024 ·May 2024 ·Nov 2022

      [8]
    2. b)

      Explain Recurrent Neural Networks and types of Recurrent Neural Networks.

      Also asked:Nov 2024 ·May 2024 ·Nov 2022

      [9]
  2. Q2

    1. a)

      Explain Long Short-Term Memory Networks (LSTM) in detail.

      Also asked:May 2024 ·May 2023 ·Nov 2022

      [8]
    2. b)

      Explain Encoder Decoder architectures, Recursive Neural Networks.

      [9]
  3. Q3

    1. a)

      Discuss different types of Applications of Autoencoders.

      [9]
    2. b)

      Describe Denoising Autoencoders, Contractive Autoencoders.

      [9]
  4. Q4

    1. a)

      Explain Regularized Autoencoders-Sparse Autoencoders.

      [9]
    2. b)

      State and explain Undercomplete Autoencoders.

      [9]
  5. Q5

    1. a)

      Discuss Greedy Layer wise Pre-training methods.

      Also asked:Nov 2025 ·May 2025

      [9]
    2. b)

      Explain Dense Net in detail. 2

      [9]
  6. Q6

    1. a)

      Elaborate Variants of CNN in detail.

      [9]
    2. b)

      Explain Transfer Learning and Domain Adaption.

      Also asked:Nov 2022

      [9]
  7. Q7

    1. a)

      Discuss Speech Recognition using Deep Learning.

      [9]
    2. b)

      Explain Recommender system in detail.

      [8]
  8. Q8

    1. a)

      What are Image Classification Techniques.

      [9]
    2. b)

      Explain Natural Language Processing in detail. 

      [8]