This module offers an introduction to a variety of unsupervised and supervised methods of data processing. Learn different architecture configurations for predictive modeling, kernel methods, neural networks, and techniques for evaluation of model performance. You'll bring real-world problems from your own workplace, and use machine learning to solve them. With access to the state-of-the-art resources in the Faculty of Engineering, and leading researchers in the area, your learning will be hands-on and practical with application to industry. Prerequisite: Restricted to students admitted into the Certificate for Artificial Intelligence
Representation, processing, and application of knowledge in emerging concepts of Semantic Web: ontology, ontology construction, and ontology integration; propositional, predicate and description logics; rules and reasoning; Semantic Web services; Folksonomy and Social Web; Semantic Web applications.
Architecture and basic components of computing systems. Programming environment and program development methodology. Basics of programming: from data structures and functions to communication with external devices. Principles of object-oriented programming. Good programming style. Prerequisite: ENCMP 100.
An introduction to principles of reinforcement learning that include algorithms supporting action decision processes that optimize long-term performance. Topics include: dynamic programming, Q-learning, Monte Carlo reinforcement learning, and efficient algorithms for single- and multi-agent planning. Co-requisite: EXEN 2452