Course Coordinator:Paulo Petersen Saraiva (ppetersen@usc.edu.au) School:School of Science, Technology and Engineering
UniSC Moreton Bay |
Blended learning | Most of your course is on campus but you may be able to do some components of this course online. |
Please go to usc.edu.au for up to date information on the
teaching sessions and campuses where this course is usually offered.
This course gives you a practical introduction to machine learning and deep learning. It introduces you to a variety of learning algorithms and how to use them. You will learn about the key stages of the machine learning process such as algorithm selection, feature selection, model building, diagnostics, cross-validation, and testing.
Activity | Hours | Beginning Week | Frequency |
Blended learning | |||
Learning materials – Pre-recorded concept videos and associated activity | 2hrs | Week 1 | 13 times |
Tutorial/Workshop 1 – On-Campus Computer workshop | 2hrs | Week 1 | 13 times |
300 Level (Graduate)
12 units
Course Learning Outcomes On successful completion of this course, you should be able to... | Graduate Qualities Completing these tasks successfully will contribute to you becoming... | |
1 | Explain common models and processing pipelines in machine learning applications | Knowledgeable |
2 | Apply machine learning algorithms to design solutions for real problems |
Creative and critical thinker Empowered |
3 | Compare benefits/drawbacks of different models and algorithms regarding real use cases |
Knowledgeable Creative and critical thinker Empowered |
4 | Analyse results and solutions to verify their correctness and impact on decision making | Engaged |
5 | Report model selection, implementation, and evaluation in written communication. |
Creative and critical thinker Empowered |
Refer to the UniSC Glossary of terms for definitions of “pre-requisites, co-requisites and anti-requisites”.
CSC201 and MTH212
Not applicable
Not applicable
Not applicable
Standard Grading (GRD)
High Distinction (HD), Distinction (DN), Credit (CR), Pass (PS), Fail (FL). |
Students will complete individual weekly workshop activities under the guidance of the workshop facilitator, providing opportunities for rapid formative feedback throughout the semester.
Delivery mode | Task No. | Assessment Product | Individual or Group | Weighting % | What is the duration / length? | When should I submit? | Where should I submit it? |
All | 1 | Examination - not Centrally Scheduled | Individual | 10% | 2 hours |
Week 6 | Online Assignment Submission with plagiarism check |
All | 2 | Artefact - Technical and Scientific, and Written Piece | Individual | 40% | Code implementation and a brief report to explain the model and results |
Week 11 | Online Assignment Submission with plagiarism check |
All | 3 | Artefact - Technical and Scientific, and Written Piece | Individual | 50% | Code implementation plus 1500 words |
Exam Period | Online Assignment Submission with plagiarism check |
All - Assessment Task 1:Examination | |
Goal: | The exam will develop your ability to independently apply your skills and knowledge to solve familiar problem-based questions with confidence within a set time limit. |
Product: | Examination - not Centrally Scheduled |
Format: | This examination consists of a set of questions on the use of machine learning models and algorithms. The questions are based on tutorial activities and course learning materials. |
Criteria: |
|
All - Assessment Task 2:Data modeling | |
Goal: | Apply machine learning tools to learn models from data sets |
Product: | Artefact - Technical and Scientific, and Written Piece |
Format: | You will be presented with a data-related challenge, and will use machine learning tools to learn and evaluate models from the data. |
Criteria: |
|
All - Assessment Task 3:Machine learning project | |
Goal: | You will explore a case study and apply your knowledge of machine learning to design, justify and develop an application to meet the case study requirements. |
Product: | Artefact - Technical and Scientific, and Written Piece |
Format: | 1 software application (code) satisfying the requirements of the case study and 1 report with 1500 words on design decisions justifying the chosen learning models. |
Criteria: |
|
A 12-unit course will have total of 150 learning hours which will include directed study hours (including online if required), self-directed learning and completion of assessable tasks. Student workload is calculated at 12.5 learning hours per one unit.
Please note: Course information, including specific information of recommended readings, learning activities, resources, weekly readings, etc. are available on the course Canvas site– Please log in as soon as possible.
Please note that you need to have regular access to the resource(s) listed below. Resources may be required or recommended.
Required? | Author | Year | Title | Edition | Publisher |
Required | Aurélien Géron | 2019 | Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow | 2 | O'Reilly |
Not applicable
Academic integrity is the ethical standard of university participation. It ensures that students graduate as a result of proving they are competent in their discipline. This is integral in maintaining the value of academic qualifications. Each industry has expectations and standards of the skills and knowledge within that discipline and these are reflected in assessment.
Academic integrity means that you do not engage in any activity that is considered to be academic fraud; including plagiarism, collusion or outsourcing any part of any assessment item to any other person. You are expected to be honest and ethical by completing all work yourself and indicating in your work which ideas and information were developed by you and which were taken from others. You cannot provide your assessment work to others. You are also expected to provide evidence of wide and critical reading, usually by using appropriate academic references.
In order to minimise incidents of academic fraud, this course may require that some of its assessment tasks, when submitted to Canvas, are electronically checked through Turnitin. This software allows for text comparisons to be made between your submitted assessment item and all other work to which Turnitin has access.
Eligibility for Supplementary Assessment Your eligibility for supplementary assessment in a course is dependent of the following conditions applying: The final mark is in the percentage range 47% to 49.4% The course is graded using the Standard Grading scale You have not failed an assessment task in the course due to academic misconduct
Late submission of assessment tasks may be penalised at the following maximum rate: - 5% (of the assessment task's identified value) per day for the first two days from the date identified as the due date for the assessment task. - 10% (of the assessment task's identified value) for the third day - 20% (of the assessment task's identified value) for the fourth day and subsequent days up to and including seven days from the date identified as the due date for the assessment task. - A result of zero is awarded for an assessment task submitted after seven days from the date identified as the due date for the assessment task. Weekdays and weekends are included in the calculation of days late. To request an extension you must contact your course coordinator to negotiate an outcome.
UniSC is committed to a culture of respect and providing a safe and supportive environment for all members of our community. For immediate assistance on campus contact SafeUniSC by phone: 07 5430 1168 or using the SafeZone app. For general enquires contact the SafeUniSC team by phone 07 5456 3864 or email safe@usc.edu.au.
The SafeUniSC Specialist Service is a Student Wellbeing service that provides free and confidential support to students who may have experienced or observed behaviour that could cause fear, offence or trauma. To contact the service call 07 5430 1226 or email studentwellbeing@usc.edu.au.
For help with course-specific advice, for example what information to include in your assessment, you should first contact your tutor, then your course coordinator, if needed.
If you require additional assistance, the Learning Advisers are trained professionals who are ready to help you develop a wide range of academic skills. Visit the Learning Advisers web page for more information, or contact Student Central for further assistance: +61 7 5430 2890 or studentcentral@usc.edu.au.
Student Wellbeing provide free and confidential counselling on a wide range of personal, academic, social and psychological matters, to foster positive mental health and wellbeing for your academic success.
To book a confidential appointment go to Student Hub, email studentwellbeing@usc.edu.au or call 07 5430 1226.
Ability Advisers ensure equal access to all aspects of university life. If your studies are affected by a disability, learning disorder mental health issue, injury or illness, or you are a primary carer for someone with a disability or who is considered frail and aged, AccessAbility Services can provide access to appropriate reasonable adjustments and practical advice about the support and facilities available to you throughout the University.
To book a confidential appointment go to Student Hub, email AccessAbility@usc.edu.au or call 07 5430 2890.
For more information on Academic Learning & Teaching categories including:
For more information, visit https://www.usc.edu.au/explore/policies-and-procedures#academic-learning-and-teaching
UniSC is committed to excellence in teaching, research and engagement in an environment that is inclusive, inspiring, safe and respectful. The Student Charter sets out what students can expect from the University, and what in turn is expected of students, to achieve these outcomes.