Registry

Module Specifications

Current Academic Year 2012 - 2013
Please note that this information is subject to change.

Module Title	Introduction to Artificial Intelligence
Module Code	CA300
School	School of Computing
Online Module Resources
Module Co-ordinator	Semester 1: Mark Humphrys Semester 2: Mark Humphrys Autumn: Mark Humphrys
Module Teacher	Mark Humphrys
NFQ level	8	Credit Rating	5
Pre-requisite	None
Co-requisite	None
Compatibles	None
Incompatibles	None

Description

To introduce students to the definition of Artificial Intelligence (AI), debates in the Philosophy of Mind, the prospects of AI, what defines AI as distinct from other parts of Computer Science, and some basic algorithms in search, learning and evolution.To implement these ideas in a competitive internet-based project (in any programming language - though some tools are provided for Java).

Learning Outcomes

1. Identify what type of problems are suitable for an AI approach (search, learning, self-modification of some sort).
2. Evaluate the scale / dimensionality / searchspace size of such problems
3. Define the search space in such problems
4. Evaluate which AI methods are suitable for a given problem
5. Logically estimate the division of labour needed between human effort (searchspace definition, pruning, heuristic design) and machine effort (how much of the space the machine will search in the time available)
6. Apply some of the techniques covered in the course (search, learning, evolution)
7. Code the techniques in the course in the student's preferred programming language
8. Test the techniques in an Internet-based system with a massive search space and multiple conflicting goals

Workload	Full-time hours per semester
*Type*	*Hours*	*Description*
Laboratory	12	No Description
Lecture	24	No Description
Independent learning time	89	No Description
Total Workload: 125

All module information is indicative and subject to change. For further information,students are advised to refer to the University's Marks and Standards and Programme Specific Regulations at: http://www.dcu.ie/registry/examinations/index.shtml

Indicative Content and Learning Activities

Philosophy of AI..
History of AI..

Machine Learning..
Neural Networks, Back-propagation..

Other forms of learning..
Machine Evolution..

Genetic Algorithms..
Other forms of evolution..

Summary - Solution spaces, heuristic search, learning and evolution..
Architectures of autonomous agents..

The World-Wide-Mind (Porject)..

Assessment Breakdown
Continuous Assessment	30%	Examination Weight	70%

Course Work Breakdown
Type	Description	% of total	Assessment Date
Assignment	Internet based programming project to solve AI problem	30%	Once per semester

Reassessment Requirement
Resit arrangements are explained by the following categories; 1 = A resit is available for all components of the module 2 = No resit is available for 100% continuous assessment module 3 = No resit is available for the continuous assessment component
This module is category 1

Indicative Reading List