Dr. Brian Mac Namee
Home Research Publications Teaching
  DT228/4 Graphics & Image
  Processing
  DT217 Problem Solving,
  Communication & Innovation
  Final Year Projects
  DT286 Machine Learning   MSc Visualisation   DT286 Probability &
  Statistical Inference


DT286 Machine Learning

The Machine Learning module takes an in-depth look at various inductive machine learning algorithms including supervised approaches to classification and regression, unsupervised approaches to clustering and segmentation and semi-supervised approaches such as active learning.

All up to date notes are made available to students on Webcourses. For reference the notes from the 2010 - 2011 academic year are available here:

1: Introduction to Machine Learning Part I Part II
2: Instance-based Learning Part I Retail Example Part II Video Example Part III
3: Information Theory & Decision Trees Part I Decision Tree Tool Restaurant Data For those interested original papers on information theory Hartley, 1928 Shannon, 1948
4: Probability Based Learning Part I Part II Part III Part III (B & W) Part IV Part IV (B & W)
5: Error Reduction Based Learning Part I Part I (B & W) Part II House Price Regression Example First Derivative Example Derivative Examples Non-Linear Regression Example Linear Classification Example
6: Neural Networks Part I Part I (B & W) Part II Part II (B & W)
7: Evaluation Part I

Revision Questions: The following files contain revision questions and solutions for each of the topics covered in the course.

Machine Learning Assignment: In this assignment you will be required to demonstrate your knowledge of machine learning techniques, your ability to apply technical skills to build actual machine learning models, and your capacity to evaluate state-­of-the­?art machine learning approaches. The assignment is composed of three tasks each of which is based on a real application of machine learning techniques within the telecoms industry.

Materials required for the assignment are as follows:

2006-2007 Business Systems Intelligence Lectures:

For student's information the complete set of lecture slides from the 2006-2007 Business Systems Intelligence course, which covers some related material but not in nearly as much depth as the machine learning course, are available below.

Lecture 1: Introduction ppt
Lecture 2: Data Preparation ppt
Lecture 3: Data Warehousing ppt
       Resources: Overview Paper
Lecture 4: Data Association ppt
       Resources: Association Analysis Book Chapter ACM Association Mining Paper
Lecture 5: Classification 1 ppt
       Resources: Classification Book Chapter
Lecture 6: Classification 2 ppt
Lecture 7: BI Schemes ppt
Lecture 8: Wrap-Up ppt