CP5191 MACHINE LEARMNG TECHNIQUES January 2018 Question Paper

Anna University Chennai M.E / M.Tech. DEGREE EXAMIINATION 01st Semester CSE CP5191 MACHINE LEARMNG TECHNIQUES January 2018 Question Paper Free Download

Anna University Chennai

Question Paper Code : 47118

M.E / M.Tech. DEGREE EXAMIINATION, JANUARY 2018

First Semester

Computer Science and Engineering

CP 5191 MACHINE LEARMNG TECHNIQUES

(Common to M.E. Computer Science and Engineering With Specialization in Networks)

(Regulations 2017)

Time: Three Hours 

Maximum : 100 Marks

Answer ALL questions

PART - A (10x2=20 Marks)

1. List out the types of machine learning.

2. Define perceptron.

3. What is a spline ?

4. State the applications of radial basis function network.

5. Write the concept behind ensemble learning.

6. Distinguish between classification and regression.

7. What is dimensionality reduction

8. Define evolutionary computation. 

9. What is sampling ?

10. Define Bayesian network.

PART-B (5 x 13 = 65 Marks)

11. a) .Describe the perspectives and issues in machine learning.

b) Discuss linear regression with an example.

12. a) Explain multi-layer perceptron model with a neat diagram.

(OR)

b) Describe the working behaviour of support vector machine with diagrams

13. a) Elaborate on Classification and Regression Trees (CART) with examples.

(OR)

b) Summarize K-means algorithm and group the points (1, 0, 1), (1, 1, 0), (0, 0, 1) and (1, 1, 1) using K-means algorithm.

14. a) Describe how principal component analysis is carried out to reduce dimensionality of data sets.

(OR)

b) i) Write short notes on reinforcement learning. (5)

ii) What is meant by isomap ? Give its significance in machine learning. (8)

15. a) Discuss Markov Chain Monte Carlo Methods in detail.

(OR)

b) Explain hidden Markov models in detail.

PART-C (1x15=15 Marks)

16. a) Choose two destination with different routes connecting them. Apply genetic algorithm to find the optional path based on distance.

(OR)

b) Use decision tree to classify the students in a class based on their academic performance. 

Share This