CPSC 422 Intelligent Systems
Winter Session 2006/2007 Term 2
Building on material from CPSC 312 and CPSC 322, this
course explores the science and technology developed for designing and
implementing intelligent systems. CPSC 322 gave an overview of some AI topics
making many simplifying assumptions (e.g., concentrating on finite
feature-based representations). In this course, we investigate how to lift
various of these assumptions to cover more sophisticated domains. CPSC 312
gives both methodologies for dealing with objects and relations as well as
relational programming experience. CPSC 422 will build on the topics
in these courses.
The following topics will be addressed:
- Hierarchical Control
- Decision making and planning under uncertainty; utility, decision
networks, process models
- Reinforcement Learning
- Assumption-based Reasoning: abduction & default reasoning;
diagnosis & design;
- Using Uncertain Knowledge: probability, Bayesian belief networks,
inference, learning belief networks, dynamic belief networks, perception,
hidden Markov models, relational models
- Multi-agent systems
- Objects and relations; Ontologies, Semantic web, OWL
These topics will be presented in relation to a number of applications:
- computer games (starting from a simple grid
game)
- intelligent tutoring systems
- robot control
- knowledge-based systems
David
Poole
Email: poole@cs.ubc.ca
Office: CICSR 127
Office Hours: Tuesdays 1:00-1:50 or by appointment.
Teaching Assistants:
Jacek Kisynski <kisynski@cs.ubc.ca>. Office hours:
Mondays and Wednesdays, 2-3pm in Computer Science
Learning Centre (ICICS/CS X150).
Grading Scheme
The following is a rough guideline only. The final grading scheme may vary
slightly.
- Written Assignments 20%
- Mini projects 20% - these will be small projects done individually or
in small groups and presented to the class during term. Each person will
be expected to do 5 mini-projects.
- Midterm Exam 15%
- Project 20%
- Final Exam 25%
See the course outline or (pdf) for more details, particularly about
plagiarism.
The lectures will follow the material of Chapters 6, 7, 9,
10, 11 and 12 of the textbook. Additional
material will be supplied (particularly on planning under uncertainty and
reinforcement learning). You can also get copies of the
slides used in class,
There will be about 5-6 assignments.
We now have:
The current plan
is for the assignments to cover the following topics:
- Game Agents (decision-theoretic planning and reinforcement
learning)
- Intelligent Tutoring Systems
- Robot localization and mapping
- Semantic Web
and one literature review and a group project (or in pdf).
There are no labs or tutorials scheduled for this
course. Students should make use of Computer Science computing facilities or
any PC running Mac OS, Linux or Windows to complete homework assignments. You
will need Prolog, (e.g., SWI prolog)
and Java.
CPSC 422 (Winter 2006/2007, Term 2)