UNIT 3
RNN
Short
Answer Questions
1. List
the different types of Recurrent Neural Networks.
2. List
the different variants in of RNNs with RNN Nodes.
3. What
is the purpose of RNN?
4. List
the different applications of RNNs.
5. Define
RNN Layer.
6. Define
RNN Node.
7. List
the essential elements of RNN.
8. How
can you handle branches in RNN?
---------------------------------------------------------------------------------------------------------------------------
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)?
UNIT-1
Deep Learning: Fundamentals
Short Answer Questions
-----------------------------------------------------------------------------------------------------------------------------
1.
Define
Artificial Neural Network.
2. Define Neuron.
3.
List the
operations performed by ANN layers.
4.
List the
different applications of Deep Learning.
5.
Define
Deep Learning.
6.
List the
different applications of Artificial Neural Network.
7.
List the Building
Block of Neural Networks.
8.
Define
Dense layer.
9.
What is
loss function.
10. Identify the different layers in ANN.
11. Explain Forward Pass.
12. Explain Backward Pass.
13. List the different optimizers.
14. How to overcome vanishing and exploding
gradient problems
15. List the difficulties in convergence.
16. Define Preprocessing.
17. Define Momentum.
18. What is Learning Rate Decay?
19. What is the purpose of weight initialization?
20. What is Regularization?
21. List different Regularization techniques.
22. Define Dropout.
23. Define SoftMax activation function.
24. When we use cross entropy loss function?
25. List the different activation functions.
26. Define sigmoid activation function.
27. Define tanh activation function.
28. Define ReLU activation function.
29. How to train the neural network?
30.
Compare the ReLU
activation function with the sigmoid activation function.
