MSC Semester III - Artificial Intelligence

Unit 

Introduction to Artificial intelligence: introduction. Al techniques, problem solving with AI, Al models.data acquisition and learning aspects in Al. Problem Solving: problem-solving process, stimulating problem, problem types and characteristics, problem analysis and representation, problem space and search. toy problems, real-world problems, problem reduction methods. Uniform search: general search algorithm, uniformed search methods - BFS, uniform cost search. DFS, Dl.S. lS, hi-directional search. comparison ofthe uniform.need techniques.

Unit 

Machine Learning: what is machine learning? Learning paradigms. learning concepts. methods and models, statistical learning methods. artificial neural networks-based learning, support vector machines, reinforcement learning.

Unit

Expert systems: the architecture of the expert system. confidence factors, existing expert systems, knowledge acquisition, shell and e, explanations. self-explaining system. rule-based expert systems, forward and backward chaining. frame-based expert systems, uncertainty management in expert systems. expert system.) and DSS. pros and cons of expert systems, case study. Pattern Recognition: machine perception and pattern recognition, feature extraction, classification. object recognition, speech recognition. pattem machine. came Playing: important concepts of game theory. game playing and knowledge structure, the game as search problem. alpha-beta pruning, game theory problems. lobotics. Concepts and terminology o1'ANN, t'eed-tbrrvard NN, tbeclback rretworks, pattern associative networks, Competitive learning, fuzzv sets. fuzzy irttlrence process, neuro-fuzzy systems, range ofAl applications, Al applications and examples. case stud\\: agricLrltural domain - larnrer's iutelligent assistant.

.