CS365: Artificial Intelligence Programming

Instructor

Dr. Amitabha Mukerjee (amit@cse.iitk.ac.in)

Course TA

Mrityunjay Gautam (mrityu@iitk.ac.in)

Text

Prerequisites

CS 210 Data Structures.

Course Objective

This course is a project-oriented course in which only the very fundamental material will be covered. You are then expected to select a project to investigate further. The class will also learn from your work on this project, which may be either an application or a theoretical topic.

Grades

Two exams - 15% each
Homework and Labs - 20%. Expect to work hard on these.
Final Project - 50% (Breakup: Proposal: 5%, Presentation 10%, Report 15%, Demo/Oral 20%)

COURSE OUTLINE

  1. Overview of AI: "anything that the computers can't do yet." Agent models of intelligence

    [ASSIGNMENT 0: Cartoon, Doctor interaction]
    [ASSIGNMENT 1: Recent Papers - BIBLIOGRAPHY REVIEW
    [INITIAL PROJECT DISCUSSIONS]

  2. Sensing - Computer vision: Edge Detection, optical flow, Line Labeling

    [ASSIGNMENT : Canny Filter]

  3. Action: Robotics - articulated and mobile robots; motion planning, task planning.

  4. Learning Sensory-Action Schemas --> Generalizing to Abstract Schemas

    [ASSIGNMENT : Decision Trees]

  5. Competing paradigms in AI: symbolic-centralized vs reactive-distributed

  6. Statistical Approaches in AI. Bayesian Learning. Supervised vs Unsupervised Learning.

    [ASSIGNMENT : Bayesian Learning]

  7. Problem Representation, Search and heuristics. Optimality (A*). Game trees

    MID-SEM 1 AROUND HERE

  8. First-Order Predicate Calculus. Deduction systems: Classical symbolic logic. Resolution Systems.

    [ASSIGNMENT : Classical Logic]

  9. Language and Cognition: Formal Models of Semantics, Schemata
    [NOTE: MID-SEM 2 INCLUDES PROJECT CONTENT]