SIT720 - Machine Learning
Unit details
| Year: | 2022 unit information |
|---|---|
| Important Update: | Unit delivery will be in line with the most current COVIDSafe health guidelines. We continue to tailor learning experiences for each unit to achieve the best possible mix of online and on-campus activities that successfully blend our approaches to learning, working and research. Please check your unit sites for announcements and updates. Last updated: 4 March 2022 |
| Enrolment modes: | Trimester 1: Burwood (Melbourne), Waurn Ponds (Geelong), Online Trimester 2: Burwood (Melbourne), Waurn Ponds (Geelong), Online |
| Credit point(s): | 1 |
| EFTSL value: | 0.125 |
| Unit Chair: | Trimester 1: Bahareh Nakisa Trimester 2: Chandan Karmakar |
| Prerequisite: | One of SIT718, SIT731 or SIT771 |
| Corequisite: | Nil |
| Incompatible with: | Nil |
| Typical study commitment: | Students will on average spend 150 hours over the teaching period undertaking the teaching, learning and assessment activities for this unit. |
| Scheduled learning activities - campus: | 1 x 2 hour online class per week, 1 x 2 hour workshop per week. Weekly drop-in sessions. |
| Scheduled learning activities - cloud: | Online independent and collaborative learning including optional scheduled activities as detailed in the unit site. |
Content
Machine learning is an important tool in analytics, where algorithms iteratively learn from data to uncover hidden insights, without being directly programmed on where to find such information. SIT720 will allow students to explore machine-learning techniques such as data representation, unsupervised learning (clustering and factor analysis) methods, supervised learning (linear and non-linear classification) methods, concepts of suitable model complexity for the problem and data at hand. Students will have the opportunity to apply these techniques in solving real-world problem scenarios presented to them in the unit.
| ULO | These are the Learning Outcomes (ULO) for this unit. At the completion of this unit, successful students can: | Deakin Graduate Learning Outcomes |
|---|---|---|
| ULO1 | Use Python for writing appropriate codes to solve a given problem. | GLO1: Discipline-specific knowledge and capabilities |
| ULO2 | Apply suitable clustering/dimensionality reduction techniques to perform unsupervised learning on unlabelled data in a real-world scenario. | GLO1: Discipline-specific knowledge and capabilities |
| ULO3 | Apply linear and logistic regression/classification and use model appraisal techniques to evaluate develop models. | GLO1: Discipline-specific knowledge and capabilities |
| ULO4 | Use the concept of KNN (k-nearest neighbourhood) and SVM (support vector machine) to analyse and develop classification models for solving real-world problems. | GLO1: Discipline-specific knowledge and capabilities |
| ULO5 | Apply decision tree, random forest and ensemble models to demonstrate multi-class classification models. | GLO1: Discipline-specific knowledge and capabilities |
| ULO6 | Implement model selection and compute relevant evaluation measure for a given problem. | GLO1: Discipline-specific knowledge and capabilities |
| ULO7 | Use concepts of machine learning algorithms to design solution and compare multiple solutions. | GLO1: Discipline-specific knowledge and capabilities |
These Unit Learning Outcomes are applicable for all teaching periods throughout the year
Assessment
| Assessment Description | Student output | Grading and weighting (% total mark for unit) | Indicative due week |
|---|---|---|---|
| Problem-solving tasks | 2 x written programs and reports on the output | 30% (5%, 25%) | Weeks 3 and 7 |
| Projects | 2 x written reports, approximately 3,000 words | 70% (35%, 35%) | Weeks 10 and 12 |
The assessment due weeks provided may change. The Unit Chair will clarify the exact assessment requirements, including the due date, at the start of the teaching period.
Learning Resource
The texts and reading list for the unit can be found on the University Library via the link below: SIT720 Note: Select the relevant trimester reading list. Please note that a future teaching period's reading list may not be available until a month prior to the start of that teaching period so you may wish to use the relevant trimester's prior year reading list as a guide only.
Unit Fee Information
Click on the fee link below which describes you: