Module Information

Module Identifier

CS36110

Module Title

Machine Learning

Academic Year

2016/2017

Co-ordinator

Dr Christine Zarges

Semester

Semester 1

Other Staff

Course Delivery

Delivery Type	Delivery length / details
Lecture	20 x 1 Hour Lectures

Assessment

Assessment Type	Assessment length / details	Proportion
Semester Assessment	Report 1500 Words - Report given to a machine learning task, select two machines learnig techniques and discuss their applications to this task.	40%
Supplementary Assessment	Supplementary Assessment Students must resit failed assessment.	100%
Semester Assessment	Report and Application 1500 Words - Experimentation and report	60%

Learning Outcomes

On successful completion of this module students should be able to:

1. Describe important, different machine learning techniques and algorithms
2. Discuss properties and limitations of different machine learning techniques and algorithms
3. Compare different machine learning techniques and algorithms
4. Apply different machine learning techniques and algorithms and evaluate them experimentally
5. Select an appropriate machine learning technique for a given application

Brief description

The module provides an introduction to machine learning and a number of different machine learning techniques and algorithms. It puts an emphasis on practical applications of machine learning and highlights advantages, drawbacks and limitations of different techniques.

Content

1. Introduction (1 lecture)
Introduction to machine learning including example applications and classes of machine learning techniques

2. Decision Trees (approx. 3 lectures)
Introduction to decision trees (classification trees and regression trees); over-fitting; pruning; application example

3. Bayesian Learning (approx. 4 lectures)
Bayes' theorem/rule; maximum likelihood; maximum a posteriori; naive Bayes classifier; application example

4. Artificial Neural Networks (aprox. 4 lectures)
Introduction to perceptrons, and perceptron-based artificial neural networks; linear separability; activation functions; back-propagation; application example

5. Support Vector Machines (approx. 4 lectures)
maximum margin hyperplane; kernel trick; kernel functions; soft margins; application example

6. Selected Additional ML Topics (approx.. 4 lectures)
Introduction and discussion of another important machine learning technique topic, e.g., reinforcement learning, handling uncertainty, genetic programming

7. Summary and Revision (2 lectures)

Module Skills

Skills Type	Skills details
Application of Number	Inherent to machine learning
Communication	Report writing for assessment.
Improving own Learning and Performance	Inherent in practical assignment: application of an ML technique and self-assesment via test data.
Information Technology	Inherent to the module
Personal Development and Career planning	Machine learning techniques find numerous applications in the real world, the selection of the module does expand the areas for personal development and career planning in both industry, government bodies and academia.
Problem solving	Inherent in both assignments: selection of an appropriate technique to solve an ML problem.
Research skills	Inherent in practical assignment: application of an ML technique.
Subject Specific Skills	Application of ML techniques to various problems.
Team work

Notes

This module is at CQFW Level 6