School of Computer Science

Module 06-23069 (2017)

Introduction to AI

Level 1/C

Jeremy Wyatt Semester 1 10 credits
Co-ordinator: Jeremy Wyatt
Reviewer: Mark Lee

The Module Description is a strict subset of this Syllabus Page.

Outline

This module provides a general introduction to artificial intelligence, its techniques, and main subfields. The principal focus of the module will be on the common underlying ideas, such as knowledge representation, rule based systems, search, and learning. It will provide a foundation for further study of specific areas of artificial intelligence.


Aims

The aims of this module are to:

  • provide a general introduction to artificial intelligence, its techniques and its main subfields
  • give an overview of key underlying ideas, such as knowledge representation, reasoning, search, and learning
  • demonstrate the need for different approaches for different problems
  • provide a foundation for further study of specific areas of artificial intelligence

Learning Outcomes

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

  1. discuss the major issues and techniques in a variety of sub-fields of AI, such as vision, robotics, natural language processing, planning, probabilistic reasoning, and machine learning
  2. compare common AI techniques, describing their strengths and limitations
  3. apply a variety of standard AI techniques to simple examples

Restrictions

None


Teaching methods

22 hours of lectures and 11 hours of exercise class support

Contact Hours: 33


Assessment

Sessional: 1.5 hr examination (70%), continuous assessment (30%).

Supplementary (where allowed): 1.5 hr examination only (100%)


Detailed Syllabus

  1. Overview, Neural Nets single layer

  2. Neural Nets: multi-layer extension, deep nets mention

  3. Types of learning. Classification with decision Trees

  4. Discriminant classifiers: linear classifiers, support vector machines mention

  5. Regression, linear and non-linear regression mention

  6. Probabilities, Bayes theorem

  7. Markov Chains, Markov Decision Processes

  8. Reinforcement Learning

  9. Bayes Nets, Inference in Bayes Nets

  10. Naïve Bayes

  11. Un-informed Search: DFS, BFS

  12. Informed Search: Hill climbing, A*, heuristics + proof

  13. Representations: Sem nets, ontologies, ontologies w/ probs, Cyc mention

  14. Resolution theorem proving for propositional logic

  15. Predicate logic quickly, NMR and epistemic mention

  16. Planning. Goal regression, CWA, PDDL

  17. Decision theoretic planning

  18. Machine Vision

  19. Robotics


Programmes containing this module