MIT9309 Machine Learning and Optimisation Techniques
Unit Code
MIT9309
Level
Postgraduate
Campus
Sydney
Prerequisites
MIT8103 | MIT8203
Credit Points
10
Subject Description
MIT9309 Machine Learning and Optimisation Techniques provides students with a deep understanding of designing and implementing analytical solutions using machine learning and optimisation algorithms. The subject covers topics on core concepts to advanced techniques, state-of-the-art methods and tools for students to learn to analyse data and draw meaningful conclusions. Students will leverage optimization and machine learning models to identify trends, uncover opportunities, optimise operations, and gain a competitive edge.
Course Level
Level 2
Subject Type
☒ Specialisation (MIT Data Science)
☒ Elective (MIT)
Study Mode: Face to face on site
Study Load: Full-time
Learning Topics
- Machine-learning and optimisation foundations
- Classification, regression and clustering
- Decision trees, random forests and support-vector machines
- Model evaluation and tuning
- Neural networks, deep learning and natural-language processing
Subject Learning Outcomes
- Explain and apply the fundamental concepts, principles and techniques of machine learning and optimisation.
- Critically analyse machine learning and optimisation models allowing extraction of meaningful insights that support strategic decision-making.
- Implement and compare a range of core machine learning and optimisation algorithms suited to various types of data and business needs, identifying opportunities and challenges for recommending them in a business environment.
- Critically identify suitable machine learning and optimisation techniques according to patterns and trends in datasets and business field.
- Effectively communicate the functionalities, limitations, and business implications of machine learning and optimisation models to both technical and non-technical audiences.
Assessment
AIIHE uses a variety of assessment tools to guide and assess each student’s achievement of the subject learning outcomes. In this subject, students undertake portfolio this assessment is designed to bring theoretical concepts into hands-on activities, and to enhance students’ understanding of machine learning (ml) and optimisation techniques through portfolio elements that gradually allow the student to build an incremental knowledge of the subject topics, individual implementation (in-class test), and this assessment scaffolds on assessment 2, by putting in a specific context the practiced techniques of the previous assessments. These tasks assess the knowledge, applied skills, critical analysis, communication and collaborative capabilities relevant to the subject.
Summary of Assessment
- Students must attempt all assessment tasks, and achieve an overall mark of at least 50%, to pass this subject.
- Assessment in this subject is consistent with and informed by the AIIHE Assessment Policy and Procedure.
| Assessment Type | Due Date | Weighting |
|---|---|---|
| Assessment 1: Portfolio | Week 1 to 12 | 30% |
| Assessment 2: Individual Implementation (In-class Test) | Week 9 | 30% |
| Assessment 3: Group Report and Presentation | Week 11, 13 | 40% |
Learning Resources
AIIHE will update the topic coverage of the subject and the available relevant learning resources at the time of subject delivery. In the interim, AIIHE provides the following indicative list of relevant reference material. AIIHE also subscribes to eLearning Resources through the Canvas portal, and where relevant material is available, AIIHE will seek to source reference material from this system for staff and student access.
Prescribed Reading
- Geron, A. (2022). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 3rd edn. O'Reilly Media, Inc. Available on April 30 from https://raw.githubusercontent.com/data-science-projects-and-resources/Data-Science-EBooks/main/Machine%20Learning/Hands-on-Machine-Learning.pdf.
- Chong, E.K.P., Lu, W.S., Zak, S.H. (2023). An Introduction to Optimisation: With Applications to Machine Learning, (5th edn.). Wiley.
Texts and References
- Huyen, C. (2022). Designing Machine Learning Systems. O'Reilly Media, Inc.
- Theobald, O. (2024). Machine Learning with Python. Packt Publishing.