Office: 375 Science Center
Phone: 268-2377
email & IM: jets@clarkson.edu, jetsza

Course Objective: This course is a comprehensive introduction to core concepts in artificial intelligence (AI), and surveys active research areas. Topics covered include:

• Search strategies: best-first search, heuristics.
• Knowledge representation using predicate logic, semantic networks, neural nets, frames, and rules.
• Automated deduction: reasoning under uncertainty.
• Applications: problem-solving, planning, expert systems, game playing, learning, natural language understanding.

• Artificial Intelligence: A Modern Approach , by Russell & Norvig, Second Edition, Prentice-Hall, 2003. The web page associated with this textbook is at http://aima.cs.berkeley.edu/
• AIMA code is available in the directory /afs/cu/class/cs451/aima. There is a version of this in Allegro Common LISP (acl), in Java, and in Python. A freeware version of acl is available at http://www.franz.com/

You are responsible for all material discussed in class and in the reading assignments. Attendance is particularly important, and class participation is encouraged. Written homework and programming assignments are expected to be individual efforts, and are due in class on the date posted. Late programs will be accepted up to one week late, but there will be a 15% deduction in grade.

The project allows you to explore in more depth an area of AI, such as natural language understanding, computer vision, intelligent tutoring systems, neural networks, or whatever you find most interesting. You may work in teams of two on a project of sufficient scope, as approved by the instructor. A brief proposal describing your project will be due as posted on the course calendar, and the final project is due at the end of the semester.

Tentative Course Outline:

This will be subject to change.

Topic	Readings
Introduction to AI    The Turing Test; Intelligent Agents	Chapters 1 & 2
Problem Solving    State-Space Search; Heuristic Search; Game Playing	Chapters 3, 4 & 5
Knowledge & Reasoning    Predicate Calculus; Inference; Forward & Backward Chaining;    Resolution; Frame Systems and Semantic Nets	Chapters 6, 7, 9 & 10
Planning    Planning Agents; Situation Spaces	Chapter 11
Reasoning Under Uncertainty    Probabilistic Reasoning; Belief Networks; Decision Making	Chapters 14, 15 & 16
Learning & Neural Nets    Inductive Learning; Decision Trees;    Feedforward networks; Backpropagation	Chapters 18 & 20
Advanced Topics    Natural Language Understanding; Perception; Speech Recognition	Chapters 22, 24 & 26