Registry

Module Specifications

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

Module Title	Artificial Intelligence
Module Code	CA425
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 in depth to further themes in AI. To give them grounding in AI algorithms. To introduce them to some current research in AI. Lectures will make use of overhead computer projection, which will allow demonstration of programs. Students will implement a machine learning program, working in their own time.

Learning Outcomes

1. Understand AI approaches of defining solution spaces and search algorithms for those spaces
2. Understand design issues in both sensory input spaces and solution spaces, and be able to approach the design of a new such space
3. Understand the taxonomy of search algorithms, including random search, systematic search, heuristically-guided search and adversarial search
4. Understand and be able to implement reinforcement learning, supervised learning, neural networks, back-propagation, genetic algorithms, and other algorithms in machine learning and evolution
5. Be able to implement in Java or another language a reinforcement learning solution to a machine learning problem
6. Understand some of the history of AI and its algorithms, some of the debates over strategy, and issues in the architecture of autonomous agents

Workload	Full-time hours per semester
*Type*	*Hours*	*Description*
Lecture	24	No Description
Independent learning time	101	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

State-space control..
Reinforcement learning..

Probabilistic control..
Reinforcement learning with Neural Networks..

Other forms of machine learning..
Architectures for autonomous agents..

Multiple-mind systems..
Action Selection..

Open issues in AI..
The world-Wide Mind (Project)..

Assessment Breakdown
Continuous Assessment	30%	Examination Weight	70%

Course Work Breakdown
Type	Description	% of total	Assessment Date
Project	Machine learning program	30%	Sem 1 End

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