2006 Draft Course Schedule Codes j=John; p=Peter; g=Graham; m=Markus; s=Steve; a=Alan; e=everyone Week 01 17 July 2006 Introduction Lecture 01p - Course Overview Data Lecture 02p - Data Mining Overview and Process Laboratory 01j - Intro R (Lab exercises 1 and 2) Week 02 24 July 2006 Lecture 04p - Data Issues in Data Mining Lecture 05p - Data Mining Preprocessing Lecture 06p - Data Integration and Data Linkage Laboratory 02j - Loops/Functions/Distributions (Lab exercises 2 and 3) Assignment 1p 10 marks Week 03 31 July 2006 Statistical Basics for Data Mining Lecture 07j - Overview of Lectures & Laboratories Lecture 08j - Distributions and Sampling Distributions Lecture 09j - Linear and Other Models Laboratory 03j - Sampling Distributions (Lab Exercises 3 and 4) Week 04 7 August 2006 Statistics and Data Mining Lecture 10j - Generalizing from models Lecture 11j - Linear Models for Non-linear problems Lecture 12j - Multivariate ordination methods Laboratory 04j - Linear Models in R (Lab Exercises 5) Week 05 14 August 2006 Data Mining Techniques Lecture 13g - Clustering Lecture 14g - Association Rules Lecture 15g - Decision Trees + Deployment Laboratory 05j - Non-linear uses of linear models (Lab exercises 6) Week 06 21 August 2006 Lecture 16g - Boosting and Random Forests Lecture 17g - Support Vector Machines Lecture 18g - Bayes + Neural Networks Laboratory 06g - Rattle (Lab exercises 7; GW Assignment 2g 15 marks Week 07 28 August 2006 Lecture 19j - Use and Interpretation of Regression Results Lecture 20j - Use and Interpretation of Regression Results Lecture 21j - Models for Binary data -- GLMs Laboratory 07j - Data summary - traps for the unwary (Lab exercises 8) TERM BREAK Week 08 18 September 2006 Topics left over from first half semester Lecture 22j - Discrimination methods -- classical & other Lecture 23g - End-to-end and Privacy Issues Laboratory 08j - Multi-level models (Lab exercises 9) Assignment 3j 10 marks - Practical Week 09 25 September 2006 Special Topics Lecture 24a - ?Commentary on "Hastie, Tibshirani & Freedman's Lecture 25a - Elements of Statistical Learning (to be confirmed) Laboratory 09j - Discriminant methods (including trees & SVMs) -- error rate issues (Lab exercises 10) Week 10 2 October 2006 Computational Aspects of Data Mining Lecture 26m - Association Rules Lecture 27m - MARS Laboratory 10j - Ordination & Clustering methods (Lab exercises 11) Assignment 4j 15 marks Week 11 9 October 2006 Lecture 31p - Privacy-preserving data mining Lecture 32e - Wrap up and Survey and Feedback Laboratory 11j - Data exploration & discrimination - a `large' dataset (Lab exercises 12) Week 12 16 October 2006 Student Presentations - 20 Marks Lecture 33e - 3 Presentations Lecture 34e - 3 Presentations Week 13 23 October 2006 Lecture 35e - 3 Presentations Lecture 36e - 3 Presentations Exam e - 30 marks Take Home exam