Machine Learning
Duration
- One Semester or Equivalent
Contact hours
- 48 hours
On-campus unit delivery combines face-to-face and digital learning.
Aims and objectives
This unit aims to develop and enhance students’ conceptual and practical understanding of machine learning (ML) in the contexts of industry-relevant applications where ML has emerged to play a key role. The students will learn about fundamental concepts, key techniques and popular tools in ML as well as how real-world problems are cast into ML tasks. They will also acquire the ability to apply ML techniques and tools to solve industry-relevant problems.
Unit Learning Outcomes | |
---|---|
On successful completion of this unit students will be able to: | |
# | Unit Learning Outcome Description |
ULO1 | Demonstrate advanced knowledge of fundamental concepts, key techniques and popular tools in machine learning |
ULO2 | Critically evaluate the roles of machine learning in various real-world applications |
ULO3 | Critically analyse, evaluate and apply appropriate machine learning techniques and tools to solve various industry-relevant problems |
ULO4 | Communicate effectively as a professional to technical and non-technical audiences |
Unit information in detail
- Teaching methods, assessment and content.
Teaching methods
All Applicable Locations | |||||
---|---|---|---|---|---|
Activity Type | Activity | Total Hours | Number of Weeks | Hours Per Week | Optional - Activity Details |
Face to Face Contact | Lecture | 24 | 12 weeks | 2 | No Description |
Face to Face Contact | Tutorial Labs | 24 | 12 weeks | 2 | Tutorials in Computer Labs |
Unspecified Learning Activities | Independent Learning | 102 | 12 weeks | 8.5 | No Description |
Total Hours: | 150 | Total Hours (per week): | 12.5 |
Assessment
All Applicable Locations | |||||||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| |||||||||||||||||||||||||
| |||||||||||||||||||||||||
|
Content
- Foundations of machine learning, e.g., development history and basic concepts
- Machine learning in real-world applications
- Fundamental machine learning techniques: supervised learning and unsupervised learning
- Advanced machine learning techniques: reinforcement learning, deep learning and transfer learning
- Popular machine learning tools and computing platforms
- Applications of machine learning in various industry-relevant scenarios such as computer vision, natural language processing and Internet of Things
Study resources
- References.
References
A list of reading materials and/or required texts will be made available in the Unit Outline.