AI

UNIT-1

What is AI? , Intelligent agents: Agents and environments, Types of Agents, Problem Solving:
Representation of problem in state-space, Uniformed-search strategies: Breadth-Frist Search, Depth-
First Search, Uniform Cost Search, Depth Limited Search, Iterative Deepening search

UNIT-2 Informed Search Strategies: Heuristic Search, Greedy Search, A*, AO*, Means-End Analysis,
Heuristic Functions, Hill Climbing Search, Crypt Arithmetic

UNIT-3 Knowledge & Reasoning: Knowledge-Based Agent, The UMPUS World Environment,
Representation, Reasoning & Logic, Propositional Logic, First-Order Logic: Syntax & Semantics:
Examples

UNIT-4 Predicate Logic: Forward and Backward Chaining, Resolution & Question and Answering:
Representing knowledge using Rules, Procedural Vs Declarative Knowledge.

UNIT-5 Uncertain Knowledge & Reasoning: Handling Uncertain Knowledge, Prior Probabilities,
Conditional Probabilities, Bayes Rules (Combining Evidences), Belief Network: Construction,
Induction Learning, Learning from Decision Trees

Text Book

1. Artificial Intelligence - A Modern Approach, Stuart Russell and Peter Norvig, Third edition,
Pearson, 2014.

Reference Books

1. Introduction to Artificial Intelligence and Expert Systems, Dan W Patterson, Pearson, 2015.

2. Artificial Intelligence, Elaine Rich, Kevin Knight and Shivashankar B Nair, Third edition, McGrawHill
Education, 2015.
MACHINE LEARNING

UNIT-1

Well-posed learning problems, Designing a learning system, A concept learning task, Concept
learning as search, Find-S: Finding a maximally specific hypothesis, Version spaces and candidate-
elimination algorithm & Remarks, Inductive Bias.

UNIT-2 Decision tree learning: Representation, Appropriate problems for decision tree learning,
Basic decision tree learning algorithm, Hypothesis space search, Inductive bias, Issues, alignment

UNIT-3 Artificial Neural Networks: Representation, Appropriate problems for neural network
learning, Perceptrons, Multilayer networks and Backpropagation algorithm & Remarks.

UNIT-4 Evaluating hypotheses - Motivation, Estimating hypothesis accuracy, Basics of Sampling

theory, Bayes theorem, Concept learning, Maximum likelihood and Least-Squared error hypotheses,
Maximum Likelihood hypotheses for predicting probabilities, Bayes Optimal Classifier, Naive Bayes
Classifier.

UNIT-5 Instance based learning: k-nearest neighbor learning, Locally weighted regression, Radial
basis functions, Analytical learning: Introduction, Reinforcement Learning: Introduction

Text Book

1. Machine Learning, Tom M Mitchell, McGrawHill education, Indian edition, 2016.

Reference Books

1. Introduction to Machine Learning 3rd Edition, Ethem Alpaydin, PHI, 2015.

2. Machine Learning in Action, Peter Harrington, Manning Publications, 2012.