Scribd
Upload
27 views3 pages

55939/CTV9B: November 2015

The document outlines the structure and requirements for a 3 hour exam on neural networks with 75 total marks. The exam consists of 3 parts: Part A contains 10 multiple choice questions worth 1 mark each, Part B contains 5 short answer questions worth 5 marks each, and Part C contains 4 long answer questions worth 10 marks each. Part A focuses on basic definitions, Part B requires short notes and explanations of concepts, and Part C involves explaining topics and algorithms in detail. The exam covers a range of neural network topics including architectures, learning approaches, representations, and specific algorithms.

Uploaded by

Bharathi Indhu
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
27 views3 pages

55939/CTV9B: November 2015

The document outlines the structure and requirements for a 3 hour exam on neural networks with 75 total marks. The exam consists of 3 parts: Part A contains 10 multiple choice questions worth 1 mark each, Part B contains 5 short answer questions worth 5 marks each, and Part C contains 4 long answer questions worth 10 marks each. Part A focuses on basic definitions, Part B requires short notes and explanations of concepts, and Part C involves explaining topics and algorithms in detail. The exam covers a range of neural network topics including architectures, learning approaches, representations, and specific algorithms.

Uploaded by

Bharathi Indhu
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/ 3

NOVEMBER 2015 55939/CTV9B

Time : Three hours Maximum : 75 marks

PART A — (10 × 1 = 10 marks)


Answer any TEN questions.

1. Define Artificial Neural Networks.

2. Distinguish between supervised and unsupervised


learning.

3. What are the design parameters of ANN?

4. Define Adaptive system.

5. What is rule based neural networks?

6. List few applications of NN.

7. Mention some knowledge based approaches of


incremental learning.

8. What is heuristics?

9. What is pattern vector?

10. Define: Generalization.

11. What is competitive learning networks?

12. Define the term clustering.


PART B — (5  5 = 25 marks)

Answer any FIVE questions.

13. Give short account on basic concepts of neural


networks.

14. Write short notes on neural approaches to


computation.

15. Draw the architecture of Back propagation


Network.

16. Explain about any two knowledge based


approaches of incremental learning.

17. What is meant by parallel models? Explain.

18. What is meant by symbolic method? Explain in


detail.

19. Explain in detail about learning procedures of


structures.

PART C — (4  10 = 40 marks)

Answer any FOUR questions.

20. Explain different ways of representing the data in


the neural network systems.

21. Explain the difference between supervised and


unsupervised learning.

2 55939/CTV9B
22. Develop a Quick prop learning algorithm.

23. Explain in detail about mathematical modelling of


increment learning.

24. What is Hybrid model? Explain in detail.

25. Explain about Spatio – temporal Neural


Networks.

———————

3 55939/CTV9B

You might also like