CMPUT 366 (Intro AI) Course Outline
General Information
Term: Fall, 2007 (Lecture A1)
Date and Time: Tu/Th 2-3:20pm
Location: CSC B-10
Number of credits: 3
Useful Pointers
Lecture
Notes (Syllabus)
Assignments
Current
marks (Gradebook)
(Login = CCid account; password = student id --
feel free to change this!)
CMPUT
366 Newsgroup
Contact
Instructor: R Greiner
Office: Ath 3-59
Phone: 492-5461
E-mail: greiner at cs.ualberta.ca
Office Hours: 3:20-4:20 Tu/Th
| Teaching Assistants: | email (all @cs.ualberta.ca |
| Saman Vaisipour | vaisipou |
| Chonghai Wang | chonghai |
| David Schnizlein | schnizle |
To contact Prof + TAs: c366@ugrad.cs.ualberta.ca
View other contact information.
Overview
This course provides an introduction to artificial intelligence, with an emphasis on the design of agents that act intelligently -- ie, that "do the right thing" in complex environments, by acting optimally given the limited information and computational resources available. We will focus on agents that can reason (eg, answer queries, or produce plans) from their stored knowledge, using logic-based and/or probability-based techniques as appropriate. If time permits, we will also discuss how these agents can perceive the world (understanding visual scenes and/or natural language), and can learn (acquire new information) from their observations and experiences.
Objectives
Any student who understands the material in this course will understand the foundations of artificial intelligence (AI), and many of the standard computational tools available. That person will be able to apply these ideas and tools in novel situations -- eg, to determine whether any AI methods apply to this situation, and if so, which will work most effectively. He or she will also be able to assess claims made by others, with respect to both software products and general frameworks, and also be able to appreciate some new research results.
Pre-requisites
We assume all students know C, C++, JAVA and Matlab, and have successfully passed CMPUT 201 and 204 and STAT 221. In addition, knowledge of Lisp and Prolog may also be useful. Students who are interested in the material but do not have the required prerequisites are encouraged to talk to the instructor.
Course Topics
With a focus on "AI as the design of rational agents", topics will include
- search-based agents: uninformed search, heuristic search, constraint satisfaction, local/stochastic search (GSAT)
- logical agents: "Wumpus world", building/using logical knowledge bases, planning
- decision-theoretical agents: probability, belief nets, influence diagrams, Markov decision processes, dynamic belief/decision networks
- Other topics, as time permits:
- learning agents: foundations (PAC-learning/Bayesian learning), learning decision trees/neural nets/belief nets, reinforcement learning. (This material will be covered in depth in Cmput466 )
- perception: vision, natural language understanding, ...
Course Work and Evaluation
There will be 4 assignments, and 1 Final; see course schedule for the details.
Grading System
During the term, your marks will be accumulated out of 100%, as indicated in this table.
At the end of the term, you will be assigned a letter grade. The mapping from term mark (out of 100%) and final letter grade (corresponding to the 4-point scale) will be consistent with university guidelines, but there is no a priori distribution or formula. See 61.6 University of Alberta Marking and Grading Guidelines.
Deferred Exams
If necessary, will be scheduled according to regulations.
Re-Evaluation
If you have any questions or concerns about your marks on a particular assignment, you must contact the TA who graded this assignment, within 7 days of the mark being posted. After that, we will not consider remarking or re-evaluating the work. (Note also that we reserve the right to re-evaluate the entire assignment, not just a single question.)
Course Materials
Policy
Course Outlines
Policy about course outlines can be found in Section 23.4(2) of the University Calendar.
Academic Integrity
The University of Alberta is committed to the highest standards of academic integrity and honesty. Students are expected to be familiar with these standards regarding academic honesty and to uphold the policies of the University in this respect. Students are particularly urged to familiarize themselves with the provisions of the Code of Student Behaviour (online at www.ualberta.ca/secretariat/appeals.htm) and avoid any behaviour which could potentially result in suspicions of cheating, plagiarism, misrepresentation of facts and/or participation in an offence. Academic dishonesty is a serious offence and can result in suspension or expulsion from the University. (GFC 29 SEP 2003)
Collaboration
In CMPUT 366, collaboration on assignments is allowed, even encouraged. This means that you can freely discuss with other students the concepts involved and even how they may be solved. The purpose of allowing collaboration is for students to learn from each other, and to understand the course material through discussion with fellow students. However, you must write your own answers, and your own code. You may NOT submit someone else's work with your name on it as if it is your own. Our advice: during your meeting, do not write down notes. See also Dept Collaboration Policy.
You are welcome to comb the web for relevant material.
However, if you use any of this material, you must be sure to give
credit.
Please, look at the definition of plagiarism and cheating in the
Code of Student Behaviour.
We assume that you are familiar with the content of that document.
Late Policy
We will excuse a total of 4 late days, over all of the assignments.-
(Eg, if HW#1 was due on 5/Oct, and HW#3 was due
on 21/Nov, then you could hand-in HW#1 1 day late [by midnight 6/Oct],
and HW#4 3 days late [midnight 24/Nov], without penalty.)
Department Policies
Refer to Department Policy to learn about:
- Collaboration
- Excused Absences
- Conditions of Use
University Policies
The University of Alberta policies include, but are not limited to, the following:
