Skip to content
InsemOct 20222019 patternBE IT

Deep Learning (DL) SPPU Insem Question Paper Oct 2022

All 4 questions from this SPPU insem paper, as printed. Read them here or open the PDF.

Subject code
414443
Pattern
2019 pattern
Exam
Insem
Session
Oct 2022
Max. marks
30
Time
1 Hour
Semester
VII
Paper code
Oct-22/BE/Insem - 105

Printed for: B.E. (Information Technology)

Instructions to the candidates

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

Questions

  1. Q1

    1. a)

      Draw and explain the architecture of Multilayered Feedforward Neural network.

      [5]
    2. b)

      What is the need of Regularization? Explain Dropout Regularization.

      [5]
    3. c)

      Explain the concept of gradient based Learning.

      [5]
  2. Q2

    1. a)

      What is the problem of vanishing Gradient? Describe various solutions to this problem.

      Also asked:Sep 2024

      [7]
    2. b)

      Explain the working of an Artificial neuron. Also explain the activation functions ReLU and LReLU.

      [8]
  3. Q3

    1. a)

      Illustrate Convolution operation in CNN with an example.

      [5]
    2. b)

      Explain the use of padding and strides in pooling layers.

      [5]
    3. c)

      What is the advantage of weight sharing in CNN.

      [5]
  4. Q4

    1. a)

      What are pooling layers in CNN? Illustrate Max pooling with an example.

      [5]
    2. b)

      Discuss applications of CNN.

      [5]
    3. c)

      Write short note on AlexNet.  

      [5]