Course Description

The course introduces the ideas and techniques underlying the principles and design of artificial intelligent systems. The course covers the basics and applications of AI, including: design of intelligent agents, problem solving, searching, knowledge representation systems, probabilistic reasoning, neural networks, machine learning and natural language processing.

Course Objectives

Learn about computer systems that exhibit intelligent behavior; design intelligent agents; identify AI problems and solve them; design knowledge representation and expert systems; design neural networks for solving problems; identify different machine learning paradigms.

Course Contents

1. Unit I: Introduction

3 hrs

1.1. Artificial Intelligence (AI), AI Perspectives: acting and thinking humanly, acting and thinking rationally

1.2. History of AI

1.3. Foundations of AI

1.4. Applications of AI

2. Unit II: Intelligent Agents

4 hrs

2.1. Introduction of Agents, Structure of Intelligent Agent, Properties of Intelligent Agents

2.2. Configuration of Agents, PEAS description of Agents

2.3. Types of Agents: Simple Reflexive, Model Based, Goal Based, Utility Based

2.4. Environment Types: Deterministic, Stochastic, Static, Dynamic, Observable, Semi-observable, Single Agent, Multi Agent

3. Unit III: Problem Solving by Searching

9 hrs

3.1. Definition, Problem as a state space search, Problem formulation, Well-defined problems

3.2. Solving Problems by Searching, Search Strategies, Performance evaluation of search techniques

3.3. Uninformed Search: Depth First Search, Breadth First Search, Depth Limited Search, Iterative Deepening Search, Bidirectional Search

3.4. Informed Search: Greedy Best First Search, A* search, Hill Climbing, Simulated Annealing

3.5. Game playing, Adversarial search techniques, Mini-max Search, Alpha-Beta Pruning

3.6. Constraint Satisfaction Problems and Search

4. Unit IV: Knowledge Representation

14 hrs

4.1. Definition and importance of Knowledge, Issues in Knowledge Representation, Knowledge Representation Systems, Properties of Knowledge Representation Systems

4.2. Types of Knowledge Representation Systems, Structured Knowledge Representation Systems: Semantic Nets, Frames, Conceptual Dependencies and Scripts

4.3. Unstructured Knowledge Representation Systems: Rule Based Systems, Propositional Logic, Predicate Logic

4.4. Propositional Logic (PL): Syntax, Semantics, Formal logic-connectives, truth tables, tautology, validity, well-formed-formula, Inference using Resolution, Backward Chaining and Forward Chaining

4.5. Predicate Logic: FOPL, Syntax, Semantics, Quantification, Inference with FOPL: By converting into PL (Existential and universal instantiation), Unification and lifting, Inference using resolution

4.6. Uncertain Knowledge, Knowledge Representation in Uncertain Domain, Statistical Reasoning using Probability, Bayes' Rule and its use, Bayesian/Causal/Belief networks, Reasoning in belief networks

4.7. Fuzzy Logic

5. Unit V: Machine Learning

5 hrs

5.1. Introduction to Machine Learning, Concepts of Learning, Importance of Machine Learning

5.2. Learning From Examples, Explanation Based Learning, Learning by Analogy, Learning by Simulating Evolution (Genetic Algorithm)

6. Unit VI: Learning with Neural Networks

5 hrs

6.1. Introduction, Biological Neural Networks vs. Artificial Neural Networks (ANN), Mathematical Model of ANN, Types of ANN: Feed-forward, Recurrent, Single Layered, Multi-Layered, Applications of ANN

6.2. Learning by Training ANN, Supervised vs. Unsupervised Learning, Hebbian Learning, Perceptron Learning, Back-propagation

7. Unit VII: Applications of AI

5 hrs

7.1. Expert Systems, Development of Expert Systems

7.2. Natural Language Processing: Natural Language Understanding and Natural Language Generation, Steps of Natural Language Processing

7.3. Machine Vision Concepts

Laboratory Works

Students write programs and prepare lab sheets for most of the units. Majorly, students practice design and implementation of intelligent agents and expert systems. Students implement various search techniques, Neural Networks, and Genetic Algorithms for solving practical AI problems. Students are advised to use LISP, PROLOG, and JAVA. The lab work should be practiced for a minimum of 3 lab hours per week.

1.Intelligent Agent Design and Implementation
2.Uninformed Search Techniques
3.Informed Search and Game Playing
4.Constraint Satisfaction Problems
5.Knowledge Representation using Propositional and Predicate Logic
6.Bayesian Reasoning and Fuzzy Logic
7.Genetic Algorithm
8.Neural Network Implementation
9.Expert System Development

Text Books

1.Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach, Pearson.

Reference Books

1.George F. Luger, Artificial Intelligence: Structures and Strategies for Complex Problem Solving, Benjamin/Cummings Publication.
2.E. Rich, K. Knight, Shivashankar B. Nair, Artificial Intelligence, Tata McGraw Hill.
3.D. W. Patterson, Artificial Intelligence and Expert Systems, Prentice Hall.
4.P. H. Winston, Artificial Intelligence, Addison Wesley.

Artificial Intelligence

Artificial Intelligence

Select University

Select Program

TabFlux . Artificial Intelligence . FWU . BSc. CSIT