Skip to content
EndsemNov 20232019 patternBE E&TC

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.

Open the PDF
Subject code
404185C
Pattern
2019 pattern
Exam
Endsem
Session
Nov 2023
Max. marks
70
Time
2½ Hours
Semester
VII
Paper code
[6181]-183

Printed for: B.E. (E & TC Engineering)

Instructions to the candidates

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

Questions

  1. Q1

    1. a)

      What is batch normalization? How batch normalization works?

      [8]
    2. b)

      Explain Dropout Technique. What is intuition behind dropout?

      [9]

  2. Q2

    1. a)

      Write note on Auto Encoder. Explain Architecture of Autoencoders.

      [9]
    2. b)

      Distinguish between Autoencoders and Restricted Boltzmann Machine.

      [8]

  3. Q3

    1. a)

      What is VGG architecture? How Speed and Accuracy of VGG is greater than AlexNet. Explain.

      Also asked:May 2024

      [11]
    2. b)

      Explain any 3 Regularization techniques for Neural Networks.

      [6]

  4. Q4

    1. a)

      Explain DenseNet architecture with its advantages and disadvantages.

      Also asked:May 2024

      [10]
    2. b)

      How does Batch Normalization work?

      [7]

  5. Q5

    1. a)

      What Recurrent neural network? Explain it’s architecture in detail?

      [10]
    2. b)

      What is LSTM and it’s working? 2

      [8]

  6. Q6

    1. a)

      How does Vanishing Gradient problem occurs in RNN.

      Also asked:May 2024

      [8]
    2. b)

      What Are Generative Models? What Are Generative Adversarial Networks? Why Generative Adversarial Networks?

      [10]

  7. Q7

    1. a)

      Explain Image classification applications using Transfer leaning architect.

      [12]
    2. b)

      Explain Image recognition using deep learning.

      [6]

  8. Q8

    1. a)

      Explain sentiment analysis of any social media application?

      [9]
    2. b)

      Explain spam mail classification applications using NLP? 

      [9]