About the Course

This course will cover several advanced topics in Artificial Intelligence beyond those covered in CS580. These topics will extend existing knowledge about search, machine learning, reasoning, and situated action. Some topics are required; others may be negotiated with the class. Topics may include planning, probabilistic reasoning, reinforcement learning, evolutionary computation, advanced neural networks, natural language processing, constraint satisfaction, reactive systems, knowledge-based learning, robotics, vision, emergent behavior, and intelligent multiagent systems.

AI is a breadth-oriented field, and the goal of this course is to provide the student with sufficient breadth beyond CS580 to act as a well-versed AI researcher.

Any programming assignments, other than the final project, will be done in Common Lisp, the traditional exploratory programming language of AI. Based on experience in CS580, we assume students will be reasonably well versed in Lisp. The course may introduce other AI languages as well, including Prolog and Scheme.

Further information will appear on the Course Web Page

Requirements

The required text is Artificial Intelligence: A Modern Approach SECOND edition. This book is green, not red. The second edition differs significantly from the first edition, and I strongly suggest you consider purchasing it (for example, at Amazon.com. Many of the differences between the editions can be found here. If you are really desperate to save money, some of the most changed chapters are available online. However, this does not include the chapters on temporal learning (markov chaining etc.) or natural language processing. If I decide to cover those topics you will still need to get copies of those chapters somehow.

As we will be coding in Lisp, I very strongly recommend that you also obtain a text on basic Common Lisp. One good choice is ANSI Common Lisp by Paul Graham, ISBN: 0133708756.

Grading Policies

This course will consist of homework and projects, and two exams. The breakdown will be approximately:

Homework and Projects	50% with higher weight given to harder projects
Exams	25% Each

There will be no make-up tests for missed examinations. Late homework will be accepted but at a loss of 20% per day (homework later than 4 days, or after the last day of class, is worth nothing).