Scribd
Upload
2 views1 page

ANN Question Bank

The document is a question bank for a course on Artificial Neural Networks, covering a wide range of topics including backpropagation, activation functions, neuron architectures, and learning algorithms. It includes questions on biological versus artificial neurons, types of learning, overfitting, generative adversarial networks, and feature selection methods. The questions aim to assess understanding of both theoretical concepts and practical applications in neural networks.

Uploaded by

anjurakshit616
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
2 views1 page

ANN Question Bank

The document is a question bank for a course on Artificial Neural Networks, covering a wide range of topics including backpropagation, activation functions, neuron architectures, and learning algorithms. It includes questions on biological versus artificial neurons, types of learning, overfitting, generative adversarial networks, and feature selection methods. The questions aim to assess understanding of both theoretical concepts and practical applications in neural networks.

Uploaded by

anjurakshit616
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

CI3003: Artificial Neural Networks

Question Bank
1. Illustrate back propagation process in deep neural network with chain rule.
2. Describe the basic models of artificial neural networks each with suitable diagram.
3. Explain the basic activation functions used in Neural Network.
4. What are biological Neurons? How they help in creating artificial neuron model.
Compare and contrast biological neurons with Artificial Neural Network
5. Explain architecture of a simple artificial neuron net.
6. Mention the types of activation functions used in ANN. Explain any four activation
functions.
7. With a neat flowchart, explain the training process of perceptron network with single
output.
8. What are the basic types of neuron connection architectures? Explain any three
architectures.
9. Justify, why single layer perceptron network could not solve even XOR problem
10. Define Learning factors. Explain the learning factors in Back propagation Algorithm
11. Differentiate between Back propagation and Radial basis function Network in detail
12. Discuss the various loss functions in neural networks.
13. Discuss the Bias - Variance trade off.
14. Discuss overfitting and underfitting with an example.
15. What is a generative adversarial network? Explain the architecture of a generative
adversarial network with a diagram.
16. Why thresholding function is not used as activation function in Multilayer Feed
Forward Networks
17. Explain input layer, hidden layer & output layer computations in Backpropagation
Network.
18. What is a generative adversarial network? Explain the architecture of a generative
adversarial network with a diagram.
19. Explain ART (Adaptive Resonance Theory). Describe the different features of ART.
20. Illustrate the different Components of CL network.
21. Explain the different types of Gradients and Descent.
22. Define Learning and Memory. Explain Learning algorithm in detail.
23. Discuss briefly Mc Culloch Pitt’s artificial neuron model. Give its limitations.
24. Explain supervised, unsupervised and reinforcement Learning with example?
25. Explain associative learning and use of Boltzman machine in associative learning.
26. List advantage and disadvantage of SOM.
27. How do you choose the Scaling method used for Neural Networks?
28. Explain in brief feature selection? Discuss in details any feature selection method?

You might also like