Deep Learning: UNIT 2: CNN: Short Answer Questions

  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)?