PG-Pattern Recognition, Semester 3, First Internal Exam, September 2023

 First Internal Examination, September 2023

P.G Department of Computer applications &

Artificial Intelligence, Semester 3

AI010303 PATTERN RECOGNITION

Total weight: 30                                                                                          Time: 3 hours

Section A.

Answer any 8 questions. Each question carries 1 weight (Weight 1each)

 

1.    What is Reinforcement Learning?

Reinforcement learning is a machine learning training method based on rewarding desired behaviours and/or punishing undesired ones. In general, a reinforcement learning agent is able to perceive and interpret its environment, take actions and learn through trial and error.

2.    Explain Minimax Criterion.

The minimax criterion is the choice from a set of options that minimizes the risk of a worse-case scenario. This is often not an optimal choice as minimization of a risk can be extremely expensive and result in missed opportunities.

3.    Explain Minimum-Error-Rate classification.

                  To minimize the average probability of error, we should select the i that

maximizes the posterior probability P(ωi|x). In other words, for minimum error rate:

4.    Discuss Bayesian Decision Theory.

 

 

5.      Explain Multivariate Density Function

The general multivariate normal density in d dimensions is written as

 

                                                                                                                        (8 x 1 = 8)

Section B

Answer any 3 questions. Weight 2 each           (Weight 2 each)

 

6.    Explain about various applications of pattern recognition

Pattern recognition is the automated recognition of patterns and regularities in data. It has applications in statistical data analysis, signal processing, image analysis, information retrieval, bioinformatics, data compression, computer graphics and machine learning

7.    Distinguish between Supervised and Unsupervised learning method.

The main difference between supervised and unsupervised learning: Labeled data. The main distinction between the two approaches is the use of labeled datasets. To put it simply, supervised learning uses labeled input and output data, while an unsupervised learning algorithm does not.

8.    Discuss two-category Classification.

Two-Category Classification. This form of the decision rule focuses on the x-dependence of the probability densities. We can consider p(x|wj) a function of wj (i.e., the likelihood function) and then form the likelihood ratio p(x|w1)/ p(x|w2).

9.    Explain Bayesian Belief Networks.

Bayesian Belief Network is a graphical representation of different probabilistic relationships among random variables in a particular set. It is a classifier with no dependency on attributes i.e it is condition independent. Due to its feature of joint probability, the probability in Bayesian Belief Network is derived, based on a condition — P(attribute/parent) i.e probability of an attribute, true over parent attribute.

 

                                                                                                                         

 

 

Section C (Essay Type Questions).

Answer any two questions. Weight 5 each

 

10.  Explain the design cycle of a pattern recognition system.

11. Explain the discriminant functions for the Normal density function.

The minimum-error-rate classification can be achieved by use of the discriminant functions