Spring 2009 Syllabus

Logistics

When:9:30-10:45 TTh
Where:CSB 425 (new CS building fourth floor, near elevator)
Instructor:Adele Howe
970-491-4192
Office hours: TBD or any time that my door is open
Office: CSB 442

Description:

The course objectives are to learn techniques and theory developed in major areas of Artificial Intelligence and to learn about the state of the art in Artificial Intelligence. The course will cover aspects of several major areas of Artificial Intelligence with an emphasis on those areas in which active research is ongoing at CSU that is not covered in other courses. The active AI research areas in our department are: genetic algorithms, neural networks, search, planning, scheduling, agents, machine learning, computer vision and bioinformatics.

Other courses offered at CSU, i.e., CS510, CS545, CS580 and CS680, cover some topics from this list. CS510 covers computer vision and advanced graphics. CS545 covers statistical machine learning. CS540 will be designed to complement CS545 and will cover some machine learning topics not in CS545 as part of the semester's topics. CS580 and CS680 cover bioinformatics and kernel methods.

The possible topics are: planning, scheduling, symbolic machine learning, genetic algorithms, data mining, agents and evaluation. The first topic in the course will be advanced search. After that what we cover depends on what students vote for..

The class is structured around a lecture format; however, class discussions, questions and participation are strongly encouraged.

Course Requirements

Textbook:

Hoos and Stutzle's Stochastic Local Search: Foundations and Applications
Other sources will be course notes and recent papers.

Pre-requisites:

CS440 or equivalent. Knowledge of fundamentals of Artificial Intelligence, search and logic.

Grading:

The course requires demonstration of student's grasp of the concepts through exams, homework assignments and a project, as follows:

Assignments (3-4)32%
Project24%
Midterms (2) 40%
Class Participation 4%
The course will be graded on a standard 90-80-70-60 distribution for grade levels. Exams may be curved if necessary. You are expected to attend class and participate in discussions. See project and assignments links for descriptions of those.

Examinations:
Two midterms. The second midterm will be either during finals week or the second to last week of classes based on a vote of the class.

Logistics Related to Grading:

Each assignment must be submitted before the beginning of class on the given deadline for that assignment (see assignment for specifics); late period for assignments will end at the start of the next following class and will incur a penalty of 8%. Assignments turned in after that time receive no credit. If you have not made prior arrangements, and you miss an exam, you will receive a zero for the exam.

I encourage you to talk with other students about your assignments and questions, but make sure you write your own programs and assignments. You may not copy another student's program (either with or without their knowledge) or write code for them. Please read the departmental policy statement regarding incompletes, cheating, and class attendance. This policy statement is in the file student info. We will follow the guidelines outlined in these documents.