Syllabus

MWF 10-11 am
Klaus 1456 2447 (note room change!)
http://cs3600.wordpress.com

Instructor: Ron Ferguson, rwf AT cc.gatech.edu Office Hours: After class on Monday and Wednesday TAs: Jie Sun, sun AT cc.gatech.edu Office hours: Mon, Wed 4:30-5:30pm Tech Square Research Building 233 or schedule via email

Required Text: Artificial Intelligence: A Modern Approach Second Edition (the green book) by Russell & Norvig, 2002 ISBN 0 13 080302 2.

---

Introduction to Artificial Intelligence is a three-credit undergraduate course on Artificial Intelligence. In particular, you will learn about the methods and tools that will allow you to build complete systems that can interact intelligently with their environment by learning and reasoning about the world.

---

ObjectivesThere are three primary objectives for the course:

• To provide a broad survey of AI and Intelligent Systems (IS)
• To develop a deeper understanding of several major topics in AI
• To develop the design and programming skills that will help you to build intelligent artifacts

In practice, you should develop enough basic skills and background that you can pursue any desire you have to learn more about specific areas in IS, whether those areas are planning, knowledge representation, machine learning, vision, robotics or other areas. In particular, this class provides a solid foundation for courses involving intelligence systems, including Machine Learning (CS4641), Knowledge-Based AI (CS4634), Computer Vision (CS4495), Robotics and Perception (CS4632), Natural Language Understanding (CS4650) and Game AI (CS4731).

Prerequisites

Someone once said that the trick to doing AI is coming up with a good representation. That’s not quite all there is to it, but it’s close enough, so to succeed at this class, you should know about data structures and algorithms. At the very least, you must be able to read pseudocode and understand basic algorithms. In addition, some basic theory helps to understand the algorithms.

As the semester continues, some familarity with basic probability theory will be useful; however, we will also review this material.

Finally, you should feel comfortable programming on your own. Most projects will be in Lisp, and perhaps one or two will be in C. We will not spend any time explaining these languages in class on the theory that at this point in your career you’re capable of doing that sort of thing on your own (and if you’re not, this is good time to learn).

The most important prerequisite for enjoying and doing well in this class is your interest in the material. If you are not sure whether this class is for you, please talk to me.

Resources

Readings. The textbook for the course is the second edition of Artificial Intelligence: A Modern Approach by Russell and Norvig. There are significiant differences between it and the first edition, so be sure to have the right edition.

Computing. You will have access to CoC clusters for your programming assignments. You can use whatever machines you want to do the work; however, the final result will have to run on the standard CoC boxes. Exactly what this means will be spelled out on each assignment. This shouldn’t be much of a restriction for you.

Web. We will use this class blog to post announcements (although last-minute announcements will be handled via email), so please check the blog every day or so (or use an RSS aggregator). Aside from that, if you want to learn more about intelligent systems or artificial intelligence, you can find out more by looking through the links on the blogroll. One good place to start is with AI on the Web.

Grading

Due dates. All graded assignments are due by the time and date indicated. Assignments can be turned in up to 48 hours late at a penalty of 15% per day. No assignment will be accepted more than 48 hours late. Sorry, but make-up exams are in general not permitted except in emergencies, and only then with proper documentation.

Grading distribution

There will be approximately 8-10 projects (for credit) and some number of homeworks (not for credit). Both may reappear on exams.

Component		Weight
Homework		0%
Projects		35%
Midterm		30%
Final		35%