Requirement
This document is designed to supplement information contained in the Module Descriptor. Student should consult the University’s requirements in addition to the following details.
MODULE SUMMARY
Aims and Summary
The purpose of this module is to provide an understanding of the design and use of intelligent agents. The module considers a wide range of application areas, which includes domains such as e-commerce and system integration. The analysis of intelligent agents identifies two sets of issues, those related to the use of Artificial Intelligence techniques and those concerned with the deployment of autonomous software. The module will explore the ways in which agents are constructed and integrated into advanced information systems. The teaching material will cover relevant techniques and will consider examples of the use of agents.
Pass Requirements
Coursework must be at least 35% and Exam must be at least 35% and Module Mark must be at least 40%
TEACHING, LEARNING AND ASSESSMENT
Intended Module Learning Outcomes
On successful completion of this module a student should be able to:
- Critically analyse the structure and architecture of agent based applications.
- Critically analyse and apply a range of AI reasoning processes.
- Design and implement an AI application using the collaborative agent based approach.
Teaching and Learning
The subject will be delivered through units consisting of lecture, on-line support reading and tutorial exercises. The tutorial exercises will be either practical lab-based exercises or requirements for critical reviews.
The module will be supported by existing facilities provided by the University computer network. The additional software required for agent development will be provided by the School.
Student activity comprises laboratory, lecture and self guided study.
Method of Assessment
The table below shows a typical assessment plan for the module. Assessment plans may vary from year to year.
Assessment Weighting Learning Outcomes
Coursework Submission
Electronic copy (in form of Microsoft Word) should be submitted to Moodle on or before the due date.
It must be stressed that all marks notified to you during the year are provisional until confirmed by the end of year Subject Assessment Board. It is possible that notified marks may be raised or lowered by this Board.
Students MUST keep copies (electronic or photocopies) of all coursework submitted on this module.
Coursework Marking Criteria
Refer to Appendix: Assessment criteria - Assessment Strategy of Coventry University [Please check with Link Tutor for the latest version]
Class Schedule
| Session | Topic | Reading |
|---|---|---|
| 1 | Six hours lecture delivered by staff. | |
| 2 | Introduction to Intelligent Agents (Lab: Jam) | Wooldridge Ch1, 2 |
| 3 | Deductive Agents, Practical Reasoning Agents (Lab: Recommender) | Wooldridge Ch 3, 4 |
| 4 | Reactive Agents, Hybrid Agents and Data mining (Lab: Recommender) | Wooldridge Ch 3, 5 |
| 5 | Agent Communication; Making Group Decisions (Lab: Assignment discussion) | Wooldridge Ch 6, 7, 12 |
| 6 | Cooperative distributed problem solving and Coordination (Lab: Assignment submission, Jade 1) | Wooldridge Ch 8 |
| 7 | Multiagent Interactions (Game Theory); Forming Coalitions (Lab: Jade 2) | Wooldridge Ch 11, 13 |
| 8 | Allocating Scarce Resource (Auctions) (Lab: Assignment discussion) | Wooldridge Ch 14 |
| 9 | Bargaining and Mobile Agents (Presentation) | Wooldridge Ch 9.4, 15 |
| 10 | Revision |
MODULE RESOURCES
Essential Reading
Wooldridge M. (2009) An Introduction to MultiAgent Systems. Second Edition. John Wiley and Sons Ltd.
Recommended Reading
Stuart J. Russell and Peter Norvig. (2009) Artificial Intelligence. A Modern Approach. Third Edition. Pearson Education Limited
Jiawei Han, Micheline Kamber, Jian Pei. (2012) Data Mining: Concepts and Techniques. Third Edition. Elsevier Inc.
Michael Nielsen. (2017) Neural Networks and Deep Learning. Available from: http://neuralnetworksanddeeplearning.com/.
Required Equipment
None
Module Handouts
Teaching & learning materials are uploaded to Moodle. Students should download his/her own copy of notes before the lecture. Worksheets will be distributed during tutorial/Laboratory sessions.