Deep Learning (DL) SPPU Insem Question Paper Sep 2024
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
- Sep 2024
- Max. marks
- 30
- Time
- 1 Hour
- Semester
- VII
- Paper code
- [6361]-101
Printed for: B.E. (Information Technology) (Insem)
Instructions to the candidates
- Answer Q.1 or Q.2, Q.3 or Q.4.
- Neat diagrams must be drawn wherever necessary.
- Figures to the right indicate full marks.
- Assume suitable data if necessary.
Questions
Q1
- a)[5]
Define Deep Learning with suitable Architecture.
- b)[5]
What is hyper parameter? Describe categories of hyper parameters?
- c)[5]
Differentiate between Single layer feed forward Neural Network and Multi Layer feed Forward Neural Network .
OR- a)
Q2
- a)[7]
Explain following Activation functions. i) ReLU ii) LReLU iii) EReLU
- b)[8]
What is the problem of vanishing gradient? Explain the various solutions to avoid it? 2
Also asked:Oct 2022
- a)
Q3
- a)[5]
Explain Alexnet architecture as per its layer.
- b)[5]
Explain types of pooling with example.
- c)[5]
Enlist and explain layers of CNN.
OR- a)
Q4
- a)[7]
Explain CNN architecture also explain functions of Hidden Layers.
- b)[8]
What is convolution operation ? Explain circular and discrete convolution operation? eeee
- a)