COSC343

Course outline

This course is an introduction to some of the central topics in Artificial Intelligence.

In the first part of the course we will look at some different definitions of intelligence, and at the concept of intelligent agents. As a way of focussing on the hard problems to be solved in AI, we will do some practical work with LEGO robots, concentrating on the issue of how to get information about the world, and how to make use of it.

In the second part of the course we will abstract away from the physical world, and look at the classical AI topics of state-space search, logic, and knowledge representation.

In the third part of the course, we will consider techniques for learning and probabilistic reasoning. Almost every human ability results from learning from experience: we will look at how these learning processes can be modelled computationally. Topics to be considered include decision trees, genetic algorithms, neural networks, Bayesian networks and Bayesian reasoning, probabilistic reasoning over time, dynamic Bayesian networks, hidden Markov models and statistical learning methods.

In the final part of the course we will spend a few lectures looking at language, a distinctively human manifestation of intelligence.