Learning Outcomes:
By the end of this module a student should be able to:
(1) Explain the underlying principles, and evaluate the advantages and limitations, of the AI approach to problem solving.
(2) Describe and implement a range of search algorithms and discuss the limitations associated with each.
(3) Apply some of the basic adversarial game playing algorithms and techniques that can be used to improve their performance characteristics.
(4) Compare and contrast alternative AI algorithms often used to solve Optimization Problems, and demonstrate that they can practically apply AI techniques such as Simulated Annealing and Genetic Algorithms.
(5) Understand what is meant by AI Planning, and show how they can represent problems using a suitable planning representation, and be capable of applying a planning algorithm to ultimately achieve a total order plan.
(6) Understand the difference between supervised and unsupervised learning Machine Learning techniques such as, Decision Trees, Naïve Bayes, kNN, K-Means, and Association Rule Mining, and describe their limitations.
(7) Distinguish between different types of Neural Networks in terms of the data they assume and the problems they are used to solve. A deeper discussion around Computer Vision and CNN Architectures is covered and students are expected to be able to carry out the various steps/calculations that are relevant here.
(8) Show that they have researched the module content beyond lectures.