Scribd
Upload
277 views2 pages

Deep Learning Question Bank for MIDTERM

The document is a question bank for a midterm exam on Deep Learning and its Applications at Swami Keshvanand Institute of Technology. It includes 2, 4, and 6 marks questions covering fundamental concepts, comparisons between models, and techniques related to neural networks and deep learning. Topics range from definitions and differences between learning types to detailed explanations of architectures and algorithms used in deep learning.

Uploaded by

nehadhaked107
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
277 views2 pages

Deep Learning Question Bank for MIDTERM

The document is a question bank for a midterm exam on Deep Learning and its Applications at Swami Keshvanand Institute of Technology. It includes 2, 4, and 6 marks questions covering fundamental concepts, comparisons between models, and techniques related to neural networks and deep learning. Topics range from definitions and differences between learning types to detailed explanations of architectures and algorithms used in deep learning.

Uploaded by

nehadhaked107
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Swami Keshvanand Institute of Technology, Management &Gramothan, Jaipur

Question Bank(I MIDTERM)

Deep Learning and its Applications(7CAI4-01)

2 Marks Questions:

1. What is Deep Learning?


2. Differentiate scalar and vector.
3. Compare Deep Learning and rule based system.
4. Give Venn diagram for Deep Learning.
5. Differentiate between Deep learning and machine learning with an example or
applications.
6. What is Deep Learning? Describe how different parts of an Artificial Intelligence system relate to
each other within different AI disciplines in detail with diagram.
7. What is stochastic gradient decent?
8. Define the term curse of dimensionality.
9. What is a neuron in a neural network?
10. What is the role of an activation function in neural networks?
11. What is a loss function?
12. What is the difference between supervised and unsupervised learning in deep learning?

4 Marks Questions:

13. Compare and contrast single layered model and multi layered perceptron model.
14. List and explain the various activation functions used in modeling of artificial neuron. Also
explain their suitability with respect to applications.
15. Point out different set of layers in Feed forward networks.
16. Explain the concept of overfitting and how regularization helps to reduce it.
17. Describe Back Propagation algorithm.
18. Explain regularization for deep learning.
19. What is backpropagation, and how does it work in training a neural network?
20. Differentiate between batch gradient descent, stochastic gradient descent, and mini-batch
gradient descent.
21. Describe overfitting and underfitting in deep learning models. What strategies can be used to
prevent overfitting?
22. How does the ReLU activation function differ from the Sigmoid function? Discuss their impact on
training deep models
6 Marks Questions:

23. Explain the architecture of pre trained CNN Models.


24. Illustrate the operation of pooling layer in CNN with simple example.
25. Explain the architecture of pre trained CNN Models. 7 3 1 2 b) Illustrate the operation of pooling
layer in CNN with simple example.
26. Explain the architecture of a Convolutional Neural Network (CNN) in detail, including the roles of
convolutional layers, pooling layers, and fully connected layers
27. Describe the process of backpropagation in neural networks. How are gradients calculated, and
how does gradient descent optimize the network's weights?
28. What is overfitting in deep learning? Discuss techniques like regularization, dropout, data
augmentation, and early stopping that help mitigate overfitting.

You might also like