| Instructor: | Derek Harter |
| Office: | Jour 208 (Lab Sci 355) |
| Phone: | 903-886-5402 (Jour 208) 903-468-8762 (Sci 355) |
| Email: | Derek_Harter@tamu-commerce.edu |
| Office Hours: | T & Th 1pm-3pm |
| Class: | T & Th 9:30 - 10:45 am Jour 204 |
This course will introduce the basic ideas and techniques underlying the design of intelligent computer systems. A specific emphasis on informed search (Hill Climbing, Genetic Algorithms, Simulated Annealing) and statistical learning methods (Bayes Networks, Neural Networks, Kernel Machines) will be presented in the class with applications to problems in robotics, autonomous agents and computational modeling of cognitive systems.
Given the interdisciplinary nature of the field, we understand that students in this course come from diverse backgrounds. While in some cases the prerequisite material will be briefly reviewed, additional assistance will be made available in sections and office hours, if possible. Course programming assignments will be in Python. We do not assume that students have previous experience with the language, but we do expect you to learn the basics fairly rapidly, see the programming page on the class website for details. However, for non CS students, alternatives to the programming assignments will be available for the class assignments.
All students should be familiar with basic concepts of computer science, including algorithms, statistical methods and computational complexity. For those who need a refresher on these topics, I plan to hold 3 special tutorials outside of the normal class meetings to help students review these materials. One tutorial will be an introduction to the basics of programming in the Python language, one will involve a review of basic mathematical concepts that are needed for the course, including complexity analysis and vector and matrix linear algebra, and one will be a review of basic probability and statistical methods. Each tutorial will be 1 hour long, and will of necessity mostly be there to help refer students to resources and concepts that they should brush up on on their own.
Students should have had undergraduate course work, or be familiar with basic statistical concepts, such as probability distributions, etc. (Math 401: Intro to Math Statistics for example). Students should have had some exposure to the basics of Linear Algebra (Math 489: Intro to Theory of Matrices).
The required course textbook is Russell and Norvig's Artificial Intelligence: A Modern Approach, Second Edition. If your copy has a red cover and not a green cover, it's the first edition and is too different to be used for this course.