Management and Information Technology


CMPT 42082

Artificial Intelligence

Status : Elective Pre-requisite : None Co-requisite : None

On completion of this course, the student should be able to:

  • Demonstrate knowledge and understanding of principal achievements and shortcomings of AI.
  • Appreciate the difficulty of distinguishing AI from advanced computer science in general.
  • Understand the main techniques that have been used in AI, and will appreciate their range of applicability.
  • Appreciate likely future developments in AI.
  • Assess the validity of approaches to model intelligent processing and the applicability of AI techniques in novel domains.
  • Select among a range of techniques for the implementation of intelligent systems.
  • Employ critical-thinking skills to relate computational to natural intelligence and to develop intelligent frameworks for problem solving.

Flavours of AI: strong and weak, neat and scruffy, symbolic and sub-symbolic, knowledge-based and data-driven.The computational metaphor: What is computation? Church-Turing thesis,The Turing test, Searle's Chinese room argument, Search: Finding satisfactory paths and outcomes.Representing Knowledge: Production rules, monotonic and non-monotonic logics, semantic nets, frames and scripts, description logics.Reasoning and Control: Data-driven and goal-driven reasoning, AND/OR graphs, truth-maintenance systems, abduction and uncertainty.Reasoning under Uncertainty: Probabilities, conditional independence, causality, Bayesian networks, noisy-OR, d-separation, belief propagation.Machine Learning: Inductive and deductive learning, unsupervised and supervised learning, reinforcement learning, concept learning from examples, Quinlan's ID3, classification and regression trees, Bayesian methods.Key Application Areas : Expert system, decision support systems, Speech and vision, Natural language processing, Information Retrieval, Semantic Web.
Lectures, tutorials and practical classes.
End-of- Semester examination, presentations and group assignments.

  1. Russell, S J and Norvig, P (2009), Artificial Intelligence: A Modern Approach, Prentice Hall.
  2. Ethem, A (2010),Introduction to Machine Learning, MIT Press.
  3. Dean, A and James, H (2011),Semantic Web for the Working Ontologist: Effective Modeling in RDFS and OWL, Morgan Kaufmann.