Machine Learning
Overview
This unit aims to develop students’ conceptual and practical understanding of the field of artificial intelligence, machine learning and deep learning in the contexts of real-world applications. The students will learn about basic concepts, key techniques and popular tools and platforms, while many real-case scenarios will be presented to be practiced. They will gain the understanding of how to identify and define a machine learning task, what is required for resolving a machine learning project, and acquire the ability to apply given techniques and tools to resolve relevant practical tasks.
Requisites
26-May-2024
Learning outcomes
Students who successfully complete this unit will be able to:
- Exhibit an in-depth understanding of core concepts, essential methods, and prevalent tools in machine learning
- Illustrate comprehension of the stages involved in a practical machine learning project, and the ability to identify and define pertinent data science tasks in real-world situations
- Conduct a thorough critical analysis, evaluation, and application of provided techniques and tools to address specified machine learning and deep learning challenges
- Effectively communicate complex technical concepts to both technical and non-technical audiences in a professional manner
Teaching methods
Hawthorn
| Type | Hours per week | Number of weeks | Total (number of hours) |
|---|---|---|---|
| On Campus Lecture |
2.00 | 4 weeks | 8 |
| Live Online Lecture |
2.00 | 8 weeks | 16 |
| On Campus Class |
2.00 | 12 weeks | 24 |
| Unspecified Activities Independent Learning |
8.50 | 12 weeks | 102 |
| TOTAL | 150 |
Assessment
| Type | Task | Weighting | ULO's |
|---|---|---|---|
| Assignment | Individual | 40 - 50% | 1,2,4 |
| Project | Individual/Group | 45 - 55% | 1,2,3,4 |
Hurdle
The assessment of this Unit is composed of assignments, in-class tests, and the final project.
To pass this Unit, students must achieve an overall grade of 50% or more, and meanwhile achieve at least 40% in the final assessment.
Students who do not achieve at least 40% in the final project will receive a maximum of 45% as the total mark for the unit.
Content
- Foundations of artificial intelligence and machine learning in real world setting
- Lifecycle of practical machine learning projects
- Data preparation for implementing machine learning techniques: concepts and tools
- Applications of given machine learning relevant techniques and tools to deal with specific machine learning relevant tasks
- Foundations of deep learning
- Basic concepts, techniques and tools of deep learning
- Applications of given deep learning relevant techniques and tools to deal with specific deep learning relevant tasks
- Machine learning versus deep learning
- Python-based implementation of ML/DL application
- Graduate Attribute – Communication Skills: Verbal communication
- Graduate Attribute – Communication Skills: Communicating using different media
- Graduate Attribute – Teamwork Skills: Teamwork roles and processes
- Graduate Attribute – Digital Literacies: Information literacy
- Graduate Attribute – Digital Literacies: Technical literacy
Study resources
Reading materials
A list of reading materials and/or required textbooks will be available in the Unit Outline on Canvas.