Scribd
Upload
129 views2 pages

NNFL

The document contains short answer questions about artificial neural networks (ANNs). It asks about key concepts like the definition of ANN, learning, activation functions, weights, bias, learning rate, excitatory and inhibitory connections, linear separability, and applications of perceptron networks. It also asks about memorization vs generalization, factors affecting backpropagation convergence, specifying different network types, and choosing the learning rate and number of neurons. Finally, it asks longer answer questions about biological neuron models, neural network architectures, specific network types, feedforward networks, learning methods, and numerical examples.

Uploaded by

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

NNFL

The document contains short answer questions about artificial neural networks (ANNs). It asks about key concepts like the definition of ANN, learning, activation functions, weights, bias, learning rate, excitatory and inhibitory connections, linear separability, and applications of perceptron networks. It also asks about memorization vs generalization, factors affecting backpropagation convergence, specifying different network types, and choosing the learning rate and number of neurons. Finally, it asks longer answer questions about biological neuron models, neural network architectures, specific network types, feedforward networks, learning methods, and numerical examples.

Uploaded by

Pratibha Dumane
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 2

Reference Questions (Short Answer)

Module 1 & 2

Questions (2m)

1. Define an artificial neural network (ANN).


2. Define learning.
3. What is the necessity of activation function?
4. What is the impact of weight in an ANN?
5. Define bias and threshold.
6. What is learning rate parameter?
7. What is the difference between excitatory and inhibitory weighted interconnections?
8. Define linear separability.
9. What are the applications of perceptron network?
10. Define epoch, iteration with reference to neural networks.
11. What is called as memorization and generalization?
12. What are the factors that can improve the convergence of learning in a back propagation
network?
13. Applications, merits , demerits of specified neural networks.
14. What is the range of values for the learning rate in an ANN?
15. Can you randomly decide whether to use supervised learning or unsupervised learning for a
given application?
16. How will you decide the number of neurons in a network for a given application?
17. What are the advantages of neural networks?
18. What is the connection between two neurons (biological) called?
19. What happens when the network is presented with a known and an unknown pattern?
20. What are the different types of activation functions?
21. Given digits 0 to 9, and you have to identify patterns, how will you do it and state the
number of neurons needed.
22. What is momentum factor?
23. What is the use of bias?
24. How does the training of a neural network differ from an if-else function?
25. What will you set the learning rate to initially?
26. What is difference between clustering and classification?
27. What is the basic difference between a digital computer and a neural network?
28. Why is bipolar representation preferred over binary representation?
29. What is the significance of sigmoid activation function?
30. List some applications of 1) Perceptron network 2) ADALINE network.

Questions (5m)

1. Describe a biological neuron model.


2. Describe the different neural network architectures.
3. Describe architectures of 1) MP Neuron 2) Perceptron 3) ADALINE .
4. Draw the architecture of a feedforward network.
5. Explain supervised, unsupervised and reinforced learning.
6. What are the different learning algorithms?
7. Numericals on MP neuron
8. Numericals on Perceptron, ADALINE network.
9. Explain the concept of linear separability.

You might also like