Scribd
Upload
1K views2 pages

Neural Networks-Question Paper

This document outlines the exam for a B. Tech degree in Computer Science and Engineering. The exam has 3 parts testing knowledge of neural networks. Part A has 5 short answer questions worth 3 marks each on topics like learning vs training and pattern analysis. Part B has 5 longer answer questions worth 5 marks each on activation functions, local minima, and network types like Maxnet. Part C has 5 longer answer questions worth 12 marks each requiring explanations and diagrams on topics like basic neuron models, backpropagation, Boltzmann machines, and network architectures like Adaptive Resonance Theory and Bidirectional Associative Memory.

Uploaded by

Sanjana
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
1K views2 pages

Neural Networks-Question Paper

This document outlines the exam for a B. Tech degree in Computer Science and Engineering. The exam has 3 parts testing knowledge of neural networks. Part A has 5 short answer questions worth 3 marks each on topics like learning vs training and pattern analysis. Part B has 5 longer answer questions worth 5 marks each on activation functions, local minima, and network types like Maxnet. Part C has 5 longer answer questions worth 12 marks each requiring explanations and diagrams on topics like basic neuron models, backpropagation, Boltzmann machines, and network architectures like Adaptive Resonance Theory and Bidirectional Associative Memory.

Uploaded by

Sanjana
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
You are on page 1/ 2

B.

TECH DEGREE EXAMINATION


Branch: Computer Science & Engineering
Eighth Semester

CS010 805G02 NEURAL NETWORKS


Time: 3 Hrs

Max. Marks: 100


Part- A
Each question carries 3 marks

1. Distinguish between Learning and Training.


2. What is pattern analysis?
3. What is meant by the momentum technique.
4. What is generalization?
5. Define Stability analysis?
(5x3=15marks)

Part- B
Each question carries 5 marks
6. What are activation functions?
7. What is meant by (i) Local minima (ii) temporal instability
8. Define Bias and Variance?
9. Explain Maxnet, Mexican Hat and Hamming Net?
10. Explain Auto and Hetero Associative Memory

(5x5=25marks)

Part-C
Each question carries 3 marks
11. Explain the basic neuron models with necessary graphical representation?

(12)

OR
12. What are the basic learning laws? Explain each in brief.

(12)

13. Explain the Back propagation learning algorithm. Also draw the architecture of the
Network

(12)
OR

14. Explain pattern classification and Regression using Multilayer Perceptron?

(12)

15. Describe the Boltzmann machine and Explain basic of Boltzmann learning law and its

significance.

(12)
OR

16. Explain the Radial Basis function networks with algorithms and applications? (12)
17. Explain the training process in the Kohonen layer and Grossberg layer of a
CPN.

(12)
OR

18. Draw and explain the architecture of Adaptive Resonance Theory.

(12)

19. Draw the architecture of Bidirectional Associative Memory (BAM) and explain in
detail.

(12)
OR

20. Draw and explain architecture of Hopfield Model.

(12)

(5 x 12= 60 marks)

You might also like