Availabilities:
Not currently available in 2018
Unit Summary
Unit type
PG Coursework Unit
Credit points
12
AQF level
Level of learning
Introductory
Former School/College
Pre-requisites
CSC72003 - Programming II OR - Fundamentals of Programming unless one of these units has been approved for advanced standing.
Unit aim
Introduces students to machine learning. Students will take an algorithmic approach to machine learning in which real-world problems will be solved through machine learning techniques. Students will familiarise themselves with a wide range of algorithms and implement them for problem solving in Python/Octave.
Unit content
Topic 1: Intro to machine learning
Topic 2: Types of machine learning
Topic 3: Regression and prediction
Topic 4: Classification
Topic 5: Neural networks
Topic 6: Machine learning: best practices
Topic 7: Philosophy of machine learning
Learning outcomes
Unit Learning Outcomes express learning achievement in terms of what a student should know, understand and be able to do on completion of a unit. These outcomes are aligned with the graduate attributes. The unit learning outcomes and graduate attributes are also the basis of evaluating prior learning.
On completion of this unit, students should be able to: | GA1 | GA2 | GA3 | GA4 | GA5 | GA6 | GA7 | |
---|---|---|---|---|---|---|---|---|
1 | identify and evaluate the evolution and recent trends in computational intelligence and machine learning | |||||||
2 | critically analyse real-world machine learning problems and compare between a range of solutions in a variety of contexts | |||||||
3 | develop, create and implement machine learning solutions to complicated problems | |||||||
4 | plan and implement parts of the tasks in a machine learning pipeline to complete a predictive analysis problem to satisfaction |
On completion of this unit, students should be able to:
-
identify and evaluate the evolution and recent trends in computational intelligence and machine learning
- GA4:
- GA5:
-
critically analyse real-world machine learning problems and compare between a range of solutions in a variety of contexts
- GA2:
- GA4:
- GA5:
-
develop, create and implement machine learning solutions to complicated problems
- GA2:
- GA4:
-
plan and implement parts of the tasks in a machine learning pipeline to complete a predictive analysis problem to satisfaction
- GA2:
- GA4: