IFN645 Machine Learning at Scale
To view more information for this unit, select Unit Outline from the list below. Please note the teaching period for which the Unit Outline is relevant.
| Unit code: | IFN645 |
|---|---|
| Prerequisite(s): | (IFN509 or IFQ509 or IFN580) OR (192cp in IV04) OR (admission into IV54) |
| Equivalent(s): | INN312 |
| Credit points: | 12 |
| Timetable | Details in HiQ, if available |
| Availabilities |
|
| CSP student contribution | $1,164 |
| Domestic tuition unit fee | $3,816 |
| International unit fee | $5,352 |
Unit Outline: Semester 2 2025, Gardens Point, Internal
| Unit code: | IFN645 |
|---|---|
| Credit points: | 12 |
| Pre-requisite: | (IFN509 or IFQ509 or IFN580) OR (192cp in IV04) OR (admission into IV54) |
| Equivalent: | INN312 |
| Coordinator: | Yue Xu | yue.xu@qut.edu.au |
Overview
The data that modern data scientists have access to is larger and more complex than in previous generations. Dealing with these data requires specialised algorithms and the use of a higher performance or cloud computing environment. This unit outlines the challenges and opportunities associated with big data and introduces machine learning algorithms that scale to large datasets. This unit will expand on the material presented in earlier data science units and students will use their programming knowledge to implement machine learning algorithms to address real world problems.
Learning Outcomes
On successful completion of this unit you will be able to:
- Discuss the challenges and opportunities associated with big data and the inability of some existing machine learning algorithms to scale to these challenging problems.
- Critically assess the strengths and limitations of machine learning algorithms and identify those appropriate algorithms to deal with different classes of problems.
- Develop data analytics solutions to apply appropriate machine learning algorithms specially tailored towards big data to solve real world problems.
- Create and deploy machine learning applications in a high-performance computing environment.
- Reflect on the ethical considerations that arise in applying machine learning in big data settings
- Work individually or in a team to implement data analytics solutions and report the findings in written formats to specialist and non-specialist audiences.
Content
In this unit you will learn about the:
- Challenges of big data (e.g. volume, velocity, veracity, variability)
- Various types of big data (e.g. text, numeric, images, videos)
- Machine learning algorithms that scale to big data
- High-performance computing environments for machine learning (e.g., cloud computing)
- Ethical concerns in big data and ethical practices in data science
- Implementation of big data analytics solutions on a high-performance computing environment
Learning Approaches
This subject will be delivered through the following means:
- Lectures (2 hours) which provide the theoretical basis of the subject
- Practicals (2 hours) which allow you to apply theory to practical (industry data-driven) problems using available software tools.
The learning process will be focused on real-world scenarios. Emphasis will be placed on theoretical work, laboratory exercises and case studies. The exercises will be designed to reinforce key concepts and to assist in the completion of assessments. Problem handling assessments will be drawn from typical industry applications and real world data sources.
Feedback on Learning and Assessment
Written feedback will be provided by teaching staff for Assessment Items 1 and 2. Informal feedback will be provided by teaching staff and peers in the weekly practical which will help for formal assessment.
Assessment
Overview
The assessments in this unit are designed for you to demonstrate a critical understanding of the machine learning concepts acquired during the lectures, as well as the application of these concepts in real-world application settings acquired during practicals. The written examination will allow you to demonstrate your understanding of the methods and challenges associated with machine learning.
Assessment criteria will be made available to you at the introduction of each assessment.
Unit Grading Scheme
7- point scale
Assessment Tasks
Assessment: Problem Solving Exercises
Short answer problem solving exercises addressing key components of the unit.
This assessment consists of three take-home problem-solving tasks throughout the semester. Each task consists of a set of short answer exercises.
This assignment is eligible for the 48-hour late submission period and assignment extensions.
Assessment: Assignment
Implement a machine learning application dealing with large datasets on a high-performance computing environment.
This assignment is eligible for the 48-hour late submission period and assignment extensions.
Assessment: Examination (Written)
Final Examination
Academic Integrity
Academic integrity is a commitment to undertaking academic work and assessment in a manner that is ethical, fair, honest, respectful and accountable.
The Academic Integrity Policy sets out the range of conduct that can be a failure to maintain the standards of academic integrity. This includes, cheating in exams, plagiarism, self-plagiarism, collusion and contract cheating. It also includes providing fraudulent or altered documentation in support of an academic concession application, for example an assignment extension or a deferred exam.
You are encouraged to make use of QUT’s learning support services, resources and tools to assure the academic integrity of your assessment. This includes the use of text matching software that may be available to assist with self-assessing your academic integrity as part of the assessment submission process.
Breaching QUT’s Academic Integrity Policy or engaging in conduct that may defeat or compromise the purpose of assessment can lead to a finding of student misconduct (Code of Conduct – Student) and result in the imposition of penalties under the Management of Student Misconduct Policy, ranging from a grade reduction to exclusion from QUT.
Requirements to Study
Costs
No extraordinary charges or costs are associated with the requirements for this unit.
Resources
Risk Assessment Statement
There are no unusual risks associated with this unit