Course Overview: This course will give an introduction to the
large and diverse field of artificial intelligence. Topics include:
problem solving by search and constraint satisfaction; alpha-beta
search for two-player games; and logic and knowledge representation,
planning, learning and decision theory, statistical machine learning,
and reinforcement learning, etc.
Prerequisites: CS 385 Algorithms or CS 182
Introduction to Computer Science Honors II
Text Books: Stuart Russell and Peter Norvig,
“Artificial Intelligence: A Modern Approach”, Third Edition,
Prentice Hall, December 11, 2009 (Required)
The students will be graded based on course participation (10%), four
homework including a midterm project (some of them need programming)
(first 2 and midterm 10%, last one 10% each adding up to 40%), and a
final project/presentation (50%). Final grade: A-- 90% to 100%; B--80%
to 89%; C-- 60% to 79%; F -- < 60%
Exponential penalty -- late for one day loses half, two day loses
another half of the remaining, and so on and so forth.
Cameras, Geometric camera models, Calibration, Radiometry,
Linear filters, Edge detection, Texture, Geometry of multiple
Motion, Segmentation, and Tracking.