Unit 1 Introduction to AI

4 lecture hours

• The AI problems
• the underlying assumption
• what is an AI techniques
• the level of the model
• criteria for success
• Some general references
• one final word

Unit 2 Problems, State Space Search & Heuristic Search Techniques

6 lecture hours

• Defining the problems as a state space search
• production systems
• Production characteristics
• production system characteristics, and issues in the design of search programs
• additional problems
• hill climbing
• best-first search
• problem. reduction
• constraint satisfaction
• means-ends analysis

Unit 3 Using Predicate Logic

6 lecture hours

• Representation simple facts in logic
• representing instance and isa relationships
• computable functions and predicates

Unit 4 Artificial Intelligence Trailblazers & Retail, Consumer Goods and Food and

• Beverage Companies: Artificial Intelligence Trailblazers Alibaba
• face book
• baidu, IBM, Microsoft
• Apple etc, Retail
• Consumer Goods and Food and Beverage Companies like Domino
• Walmart etc

Unit 5 Introduction to Prolog & Machine Learning

• Introduction To Prolog: Syntax and Numeric Function
• Basic List Manipulation Functions In Prolog
• Predicates and Conditional
• Output and Local Variables
• Iteration and Recursion
• Property Lists and Arrays
• Miscellaneous Topics
• LISP and Other AI Programming Languages
• Learning Problems
• designing a learning system
• Issues with machine learning
• Concept Learning
• Version Spaces and Candidate Eliminations
• Inductive bias

Unit 6 Subject Code

6 lecture hours

• AY 2018-19 6 Supervised and Unsupervised learning Decision Tree Representation: Appropriate problems for Decision tree learning
• Hypothesis space search in Decision tree learning
• inductive bias in Decision tree learning
• Issues in Decision tree learning K- Nearest Neighbors Learning Locally Weighted Regression
• Radial Bases
• Case Based Reasoning

Unit 7 Artificial Neural networks and genetic algorithms

6 lecture hours

• Neural Network Representation
• Appropriate problems for Neural Network Learning
• Multilayer Networks and Back Propagation Algorithms
• Remarks on Back Propagation Algorithms Case Study: face Recognition

Unit 8 Bayesian Learning

6 lecture hours

• Bayes Theorem
• Bayes Theorem and Concept Learning
• Maximum Likelihood and Least squared Error Hypothesis
• Maximum likelihood hypothesis for Predicting probabilities
• Minimum Description Length Principle
• Bayes Optimal Classifier
• Gibbs Algorithm
• Naïve Bayes Classifier
• Bayesian Belief Network
• EM Algorithm Case Study: Learning to classify text