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
- Answer Q1 or Q2, Q3 or Q4.
- Neat diagrams must be drawn wherever necessary.
- Figures to the right side indicate full marks.
- Assume suitable data, if necessary.
Questions
Q1
- a)[5]
Draw and explain the architecture of Multilayered Feedforward Neural network.
- b)[5]
What is the need of Regularization? Explain Dropout Regularization.
- c)[5]
Explain the concept of gradient based Learning.
OR- a)
Q2
- a)[7]
What is the problem of vanishing Gradient? Describe various solutions to this problem.
Also asked:Sep 2024
- b)[8]
Explain the working of an Artificial neuron. Also explain the activation functions ReLU and LReLU.
- a)
Q3
- a)[5]
Illustrate Convolution operation in CNN with an example.
- b)[5]
Explain the use of padding and strides in pooling layers.
- c)[5]
What is the advantage of weight sharing in CNN.
OR- a)
Q4
- a)[5]
What are pooling layers in CNN? Illustrate Max pooling with an example.
- b)[5]
Discuss applications of CNN.
- c)[5]
Write short note on AlexNet.
- a)