| Week | Tuesday Lecture | Extra | Thursday Lecture | Extra |
|---|---|---|---|---|
| 1 | An Informal Overview | Nature | Applications and Principles | Data |
| 2 | Concepts, Instances & Attributes | Blog Item | Knowledge Representation I | None |
| 3 | Knowledge Representation II | None | Knowledge Representation III | None |
| 4 | Algorithms: Rudimentary Rules | Holte | Algorithms: Statistical Modelling | Langley |
| 5 | Algorithms: Decision Trees | Quinlan | Algorithms: Constructing Rules | None |
| 6 | Algorithms: Association Rules | Agrawal | Algorithms: Linear Models | None |
| 7 | Algorithms: Lazy & Clustering | None | The WEKA Explorer | Project #1 | Wiki |
| 8 | Evaluating Concepts | None | Cost-sensitive Learning | None |
| 9 | Cost-sensitive Learning | None | The WEKA Experimenter | None |
| 10 | Attribute Transformation | None | Useful Transformations | None |
| 11 | A Sample Exam Paper Another Sample Exam Paper |
None | Sample Solutions No solutions for the 2010 paper |
None |
| 12 | Tutorial 1 | None | Tutorial 2 | None |
CS6405 - Datamining
| Lecturer: | Dr. Barry O'Sullivan |
| Office Hours: | By appointment through the CS Secretary. |
About this Module. This is an introduction to datamining. We will focus, specifically on building practical applications and systems. The WEKA datamining system will be used throughout the module.
Recommended Texbook. Ian Witten and Eibe Frank. Data Mining: Practical Machine Learning Tools and Techniques: Second Edition, Morgan Kaufmann, June 2005, 525 pages, Paper ISBN 0-12-088407-0.
Workload. Students must attend all lectures. Students are expected to spend at least 3 hours per week in private study.
| Lectures: | 2pm Tuesday (WGB_G18) and 2pm Thursday (WGB_G13) | |
| Coursework: |
Project #1: Spec | Data | Model;
Project #2: Spec |
Data | |
| Data-sets: | Weather | Contact Lenses | |
| Assessment: | Total marks 100: Final Year Exam 50 marks, Coursework 50 marks. |
Teaching Materials.