Project proposals due February 21 (late period until February 25). Proposal should be two pages answering these questions:
- 1. What do you want to do? 2. Why is it relevant to this class?
- 3. What implementation is involved? 4. How will you demonstrate what you've learned?
- 5. What other work is it based upon (include references)

Lecture Notes

Logistics
| When: | MWF 10:00-10:50AM |
| Where: | CS Conference room, 2nd floor USC |
| Instructor: | D. Whitley |
| 970-491-5373 |
| whitley@cs.colostate.edu |
| Office hours: Mon 2-3:30 |
| Office: USC 227 |

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 major areas of Artificial
Intelligence. The course will cover aspects of several major areas of
Artificial Intelligence. These areas are: planning, machine learning,
neural networks, genetic algorithms, computer vision, reasoning about
uncertainty and miscellaneous topics (including integrated systems and
evaluation).
The class is structured around a lecture format; however, class
discussions, questions and participation are strongly encouraged.

Course Requirements
Textbook:
Russell and Norvig's Artificial Intelligence: A Modern Approach
Pre-requisites:
Knowledge of fundamentals of Artificial
Intelligence, search and logic. Some familiarity with Common Lisp is also
recommended.
Software Requirements:
Interpreter for Common Lisp. Any Lisp
implementation should follow the Common Lisp standard. At CSU, we will
be using Allegro Common Lisp. These can be obtained by off-site
students for a number of machine types. Other implementations may be
acceptable as well; check with the instructor. For some assignments,
students will have some choice of implementation language.
Grading:
The course requires demonstration of student's grasp of the concepts
through exams, homework assignments and a project, as follows:
| Assignments | 25% |
| Project | 25% |
| Midterm I | 25% |
| Midterm II | 25% |
The course will be graded on a standard 90-80-70-60 distribution for
grade levels. Exams may be curved if necessary.
- Homework:
- Upto four homework assignments will be
assigned during the semester; one is currently planned for each
major area in the department: genetic algorithms, neural networks,
planning, and computer vision. The assignments will be
small programming projects with some writing.
- Project:
- Semester Projects may consist of an application using a publicly
available AI system or tool, overviews of new hot topics,
implementations of artificial
intelligence techniques other than those developed in class,
application of discussed techniques to real problems, or some
combination of the above. The project should include some
implementation component.
Projects must be planned with the instructor by February 21. You
may work alone or in a group of two. During the last week of the
semester, at least one person from each project will present the
project's work in front of the class. Each project must also turn in
a written report describing what was done; the report will be due on
the last day of class.
- Examinations:
- One midterm and one final exam. The final exam will cover
material since the midterm.
Logistics Related to Grading:
Each assignment must be submitted at the beginning of class on the
given deadline for that assignment; late period for assignments will
be the start of the next following class and will incur a
penalty of 10%. 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.

Course Outline and Tentative Schedule:
The following Schedule is Approximate.
Details will be filled in as the semester progresses.
| Date | Topic | Readings |
| 1/19,21 | Overview. Class requirements. | |
| 1/24-2/4 | Learning: Genetic Algorithms, GP, Local Search | Whitley article |
| 2/7-2/18 | Learning: Neural Networks and Reinforcement Learning | 19-20, Kaelbling RL tutorial(read through section 4) |
| 2/21-3/1 | Learning: inductive
learning and decision trees | 18,Dietterich |
| 3/3 | Midterm | |
| 3/6-3/10 | Spring Break! | |
| 3/13-3/24 | Reasoning: Planning | 11-12 Weld paper |
| 3/27-4/7 | Reasoning: Uncertainty | 14-15 |
| 4/10 | Interim project reports | |
| 4/12-4/14 | Natural Language | 22 |
| 4/17-4/21 | Computer Vision | 24 |
| 4/24 | Robotics | |
| 4/26 | Review | |
| 4/28 | Midterm II | |
| 5/1-5 | Class Presentations and wrap-up | |
| 5/14 | Final papers due | |