Download JNTUA B.Tech 4-2 R13 2018 April 13A04805 Pattern Recognition and Application Question Paper

FirstRanker.com

Code: 13A04805

B.Tech IV Year II Semester (R13) Regular & Supplementary Examinations April 2018

--- Content provided by FirstRanker.com ---

PATTERN RECOGNITION & APPLICATION

(Electronics and Communication Engineering)

Time: 3 hours

Max. Marks: 70

PART - A

--- Content provided by​ FirstRanker.com ---

(Compulsory Question)

*****

1. Answer the following: (10 X 02 = 20 Marks)
   1. List any three applications of pattern recognition.
   2. What are the basic steps in pattern recognition?
   3. On which Bayesian Decision theory is based?

   --- Content provided by‍ FirstRanker.com ---

   4. Explain symmetrical or zero-one loss function.
   5. List the two issues that come up for the classification accuracy with respect to dimensionality.
   6. Explain Rayleigh distribution along with their sufficient statistics.
   7. Explain a Discriminant function.
   8. What is the difference between Ho-Kashyap and modified Ho-Kashyap algorithm?

   --- Content provided by‌ FirstRanker.com ---

   9. List any two applications of HMM.
   10. Explain the sum-of-squared error criterion for clustering.

PART - B

(Answer all five units, 5 X 10 = 50 Marks)

--- Content provided by FirstRanker.com ---

UNIT - I

2. Explain the following terms associated with pattern recognition: (i) Sensing. (ii) Segmentation and grouping (along with flow chart). (iii) Mereology.
3. OR
4. Explain the concepts of supervised learning, unsupervised learning and reinforcement learning using suitable examples.

UNIT - II

--- Content provided by​ FirstRanker.com ---

4. Explain the importance of Bayesian decision theory in pattern recognition problems by taking proper examples.
5. OR
6. Explain how the action of a linear transformation on the feature space will convert an arbitrary normal distribution into another normal distribution.

UNIT - III

6. Explain how density estimation is useful in Non parametric pattern classification.

--- Content provided by⁠ FirstRanker.com ---

7. OR
8. Explain the conjunction rule of fuzzy classification and give the Cox-Jaynes axioms. List the four limitations of fuzzy classification technique.

UNIT - IV

8. Explain in detail about back propagation algorithm with respect to network learning, training protocols and learning curves.
9. OR

--- Content provided by⁠ FirstRanker.com ---

10. Show for the Widrow-Hoff or LMS rule that: if n(k) = n(1)/k, then the sequence of weight vectors converges to a limiting vector “a” satisfying Y^T (Ya - b) = 0.

UNIT - V

10. Explain Graph-theoretic method of unsupervised classification using neat diagrams.
11. OR
12. Explain the forward-backward algorithm of HMM along with the equations relating to estimates.

--- Content provided by‌ FirstRanker.com ---

*****

FirstRanker.com