UNIT II
CNN
Short Answer Questions
---------------------------------------------------------------------------------------------------------------------------
1. List
the applications of CNN.
2. Define
Convolution.
3. Define
Stride.
4. Explain
padding.
5. What
the purpose of padding?
6. Define
Kernal.
7. Define
Pooling.
8. List
the different pooling techniques.
9. Define
Flattening.
10. Define
Fully Connected Layer.
11. List
the difference between CNN and Fully Connected Layer.
12. What
is a filter (or kernel) in the context of a CNN?
13. Discuss
the role of fully connected layers in CNNs.
14.
Explain the concept of pooling in CNNs and how it
sometimes impacts output size and can cause underfitting.
15.
What is the purpose of the pooling layer
in a CNN?
16. what
are two special cases of padding? explain them with a neat diagram.
17. Discuss the
concept of convolution in CNNs.
18. How do filters
(kernels) help in feature extraction, and how are these filters learned during
the training process?
19. What is the role
of pooling in CNNs?
20. How
does pooling in CNNs reduce the spatial dimensions of feature maps?
21. Discuss
the trade-offs between using smaller and larger pooling windows in CNNs.
22. How
does the choice of pooling size affect the information retained in the feature
maps?
23. Compare max
pooling and average pooling, and explain how pooling layers help in reducing
the dimensionality of feature maps.
24.
How does pooling help to control the size of the output
feature map in a Convolutional Neural Network (CNN)?
