| Announcements | Course Info | Schedule/Slides | Assignments | FAQ | Section | Demos | Newsgroup |
This course will introduce the basic ideas and techniques underlying the design of intelligent computer systems. A specific emphasis on the statistical modeling paradigm will be presented, with applications to problems involving naturally-generated human data (such as language). See the lecture schedule for a tentative syllabus.
NOTE: This course has substantial elements of both programming and statistical methods, because these elements are central to modern AI. You should be prepared to review basic probability on your own if it is not fresh in your head. You should also be comfortable programming on the level of CS 61B even though it is not strictly required.
The required course textbook is Russell and Norvig, 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.
Coursework will consist of several substantial assignments broken into checkpoints. Assignments will have both programming and written components. Programming will be in Python; see the programming page for details. You should be prepared to do regular work each week to keep up with the material and the assignments.
Overall grades will be determined from:
Assignments must be turned in electronically by midnight on the listed due date. You will have 5 late days, up to two of which can be used for any given due date. Assignments may be done individually or in pairs. Each submission should acknowledge any collaborators and sources consulted. All code and written responses should be original. We're trusting each of you not to cheat -- we will enforce the EECS Policy on academic dishonesty (see Kris Pister's policy as well) and we will check assignments with MOSS.
Because this is a new version of this course and historical point trends are not available, final letter grades will be curved according to the professor's assessment of where the letter cutoffs should fall. However, there is no prior quota of final letter grades, so in this sense you are not in direct competition with each other.
You can find out about enrollment limits from the online schedule of classes. I expect that all qualified students will be able to take the course.
Please remember that the instructor and TAs have no control over who gets in. If you are not yet enrolled as of the first day of lecture and still want to be considered for participation in the course, you should attend class and file an appeal form by the end of the first week of classes. Appeal forms are available from the CS office on the 3rd floor of Soda Hall. (Michael-David Sasson, 379 Soda, msasson AT cs, might be able to advise you on the status of your appeal, but remember that he's quite busy.)
Here are the policies that govern admission into classes, and here are some answers to frequently asked questions about admission.
There will be several routes of communication for this course. Announcements will be posted to this web site. There is a course newsgroup, ucb.class.cs188, which is appropriate for general questions about the course, clarifications about assignments, and so on. The course staff will monitor the newsgroup, and you should send questions there whenever possible, since everyone else will be able to benefit from the answer. If you need to contact the course staff privately, you should email cs188 AT imail.eecs.berkeley.edu. You may of course contact the professor or GSIs directly, but the staff list will produce the fastest response.