Unit convenor and teaching staff |
Unit convenor and teaching staff
Convenor, lecturer
Mark Dras
Contact via email
TBA
by appointment
Lecturer
Jia Wu
Contact via email
TBA
by appointment
|
---|---|
Credit points |
Credit points
4
|
Prerequisites |
Prerequisites
Admission to MRes
|
Corequisites |
Corequisites
|
Co-badged status |
Co-badged status
ITEC873
|
Unit description |
Unit description
This unit introduces basic machine learning techniques for constructing classifiers and regression models, focusing on widely applicable standard techniques such as Naive Bayes, decision trees, logistic regression and support vector machines (SVMs), and also including more general advanced frameworks such as graphical models. We discuss in detail the advantages and disadvantages of each method, both in terms of computational requirements, ease of use and performance, and study their practical application of these methods in a number of use cases.
|
Information about important academic dates including deadlines for withdrawing from units are available at https://www.mq.edu.au/study/calendar-of-dates
On successful completion of this unit, you will be able to:
Name | Weighting | Hurdle | Due |
---|---|---|---|
Project proposal presentation | 10% | No | Week 6 |
Project proposal document | 10% | No | Week 7 |
Project presentation | 10% | No | Week 13 |
Project report | 45% | Yes | Week 15 |
Practical exercises | 25% | No | during the semester |
Due: Week 6
Weighting: 10%
This is an in-class presentation. It should provide an initial overview of the project, including in summary form the same information as in the project proposal document. The intention is that you will get feedback on your presentation that can be incorporated into the project proposal document.
You have to submit the slides of your presentation prior to the presentation via iLearn.
Due: Week 7
Weighting: 10%
This proposal should provide the following information about the project:
You have to submit the project proposal via iLearn.
Due: Week 13
Weighting: 10%
This in-class presentation should cover all aspects of the project, including results and conclusion.
You have to submit the slides of your presentation prior to the presentation via iLearn.
Due: Week 15
Weighting: 45%
This is a hurdle assessment task (see assessment policy for more information on hurdle assessment tasks)
This report should describe all aspects of the research project. It should have the format of a short scientific paper (between 5-8 pages long, plus additional pages of data or graphs if required). It should contain the following sections:
This assessment task has a hurdle requirement: you will need to obtain at least 40% for the project report in order to pass the unit. If you obtain between 30% and 40% marks for the project report, then you will be given a second (and final) attempt to submit your report.
Your have to submit the project report via iLearn.
Due: during the semester
Weighting: 25%
We expect to assign 4 practical exercises during the semester.
You have to submit the solutions to the practical exercises via iLearn.
Note that this unit assumes some prior knowledge of machine learning or a related discipline (e.g. statistics). Please contact the unit convenor if you are in doubt.
Week | Topic |
Readings (from Géron) |
Week 1 |
Welcome to unit
|
Ch 1 |
Weeks 2-3 |
Revisiting conventional machine learning
|
Ch 2-6 (selected topics) |
Weeks 4-5 |
Advanced conventional ML topics, e.g.:
|
Ch 7-8 |
Week 6 | Student presentations | |
Weeks 7-8 | Introduction to Artificial Neural Networks:
|
Ch 9-10 |
Weeks 9-10 |
Deep Neural Networks
|
Ch 11, 13 |
Weeks 11-12 |
NNs for sequences, and advanced topics:
|
Ch 14-16 |
Week 13 | Student presentations |
Macquarie University policies and procedures are accessible from Policy Central (https://staff.mq.edu.au/work/strategy-planning-and-governance/university-policies-and-procedures/policy-central). Students should be aware of the following policies in particular with regard to Learning and Teaching:
Undergraduate students seeking more policy resources can visit the Student Policy Gateway (https://students.mq.edu.au/support/study/student-policy-gateway). It is your one-stop-shop for the key policies you need to know about throughout your undergraduate student journey.
If you would like to see all the policies relevant to Learning and Teaching visit Policy Central (https://staff.mq.edu.au/work/strategy-planning-and-governance/university-policies-and-procedures/policy-central).
Macquarie University students have a responsibility to be familiar with the Student Code of Conduct: https://students.mq.edu.au/study/getting-started/student-conduct
Results published on platform other than eStudent, (eg. iLearn, Coursera etc.) or released directly by your Unit Convenor, are not confirmed as they are subject to final approval by the University. Once approved, final results will be sent to your student email address and will be made available in eStudent. For more information visit ask.mq.edu.au or if you are a Global MBA student contact globalmba.support@mq.edu.au
No extensions will be granted. Students who have not submitted the task by the deadline will be awarded a zero mark for the task, except for cases in which an application for special consideration is made and approved.
Macquarie University provides a range of support services for students. For details, visit http://students.mq.edu.au/support/
Learning Skills (mq.edu.au/learningskills) provides academic writing resources and study strategies to improve your marks and take control of your study.
Students with a disability are encouraged to contact the Disability Service who can provide appropriate help with any issues that arise during their studies.
For all student enquiries, visit Student Connect at ask.mq.edu.au
If you are a Global MBA student contact globalmba.support@mq.edu.au
For help with University computer systems and technology, visit http://www.mq.edu.au/about_us/offices_and_units/information_technology/help/.
When using the University's IT, you must adhere to the Acceptable Use of IT Resources Policy. The policy applies to all who connect to the MQ network including students.
Our postgraduates will demonstrate a high standard of discernment and common sense in their professional and personal judgment. They will have the ability to make informed choices and decisions that reflect both the nature of their professional work and their personal perspectives.
This graduate capability is supported by:
Our postgraduates will be able to demonstrate a significantly enhanced depth and breadth of knowledge, scholarly understanding, and specific subject content knowledge in their chosen fields.
This graduate capability is supported by:
Our postgraduates will be capable of utilising and reflecting on prior knowledge and experience, of applying higher level critical thinking skills, and of integrating and synthesising learning and knowledge from a range of sources and environments. A characteristic of this form of thinking is the generation of new, professionally oriented knowledge through personal or group-based critique of practice and theory.
This graduate capability is supported by:
Our postgraduates will be capable of systematic enquiry; able to use research skills to create new knowledge that can be applied to real world issues, or contribute to a field of study or practice to enhance society. They will be capable of creative questioning, problem finding and problem solving.
This graduate capability is supported by:
Our postgraduates will be able to communicate effectively and convey their views to different social, cultural, and professional audiences. They will be able to use a variety of technologically supported media to communicate with empathy using a range of written, spoken or visual formats.
This graduate capability is supported by:
Our postgraduates will be ethically aware and capable of confident transformative action in relation to their professional responsibilities and the wider community. They will have a sense of connectedness with others and country and have a sense of mutual obligation. They will be able to appreciate the impact of their professional roles for social justice and inclusion related to national and global issues
This graduate capability is supported by:
There are substantial changes compared to the offerings of 2018 and earlier. The unit now assumes some detailed technical knowledge relevant to machine learning (e.g. prior study on machine learning, knowledge of appropriate statistics, or other relevant background). Conventional machine learning will be reviewed in the first few weeks of the unit, but the majority of the unit now focuses on deep learning.
COMP783 will be graded according to the following general descriptions of the letter grades as specified by Macquarie University.
• High Distinction (HD, 85-100): Provides consistent evidence of deep and critical understanding in relation to the learning outcomes. There is substantial originality, insight or creativity in identifying, generating and communicating competing arguments, perspectives or problem solving approaches; critical evaluation of problems, their solutions and their implications; creativity in application as appropriate to the program.
• Distinction (D, 75-84): Provides evidence of integration and evaluation of critical ideas, principles and theories, distinctive insight and ability in applying relevant skills and concepts in relation to learning outcomes. There is demonstration of frequent originality or creativity in defining and analysing issues or problems and providing solutions; and the use of means of communication appropriate to the program and the audience.
• Credit (Cr, 65-74): Provides evidence of learning that goes beyond replication of content knowledge or skills relevant to the learning outcomes. There is demonstration of substantial understanding of fundamental concepts in the field of study and the ability to apply these concepts in a variety of contexts; convincing argumentation with appropriate coherent justification; communication of ideas fluently and clearly in terms of the conventions of the program.
• Pass (P, 50-64): Provides sufficient evidence of the achievement of learning outcomes. There is demonstration of understanding and application of fundamental concepts of the program; routine argumentation with acceptable justification; communication of information and ideas adequately in terms of the conventions of the program. The learning attainment is considered satisfactory or adequate or competent or capable in relation to the specified outcomes.
• Fail (F, 0-49): Does not provide evidence of attainment of learning outcomes. There is missing or partial or superficial or faulty understanding and application of the fundamental concepts in the field of study; missing, undeveloped, inappropriate or confusing argumentation; incomplete, confusing or lacking communication of ideas in ways that give little attention to the conventions of the program.
• Fail Hurdle (FH, 49): Student has obtained a raw mark over 50, yet failed all available attempts of at least one hurdle assessment (as described within Schedule 2: Unit Assessment Requirements).
The standards of achievement that will be used to assess each of the assessment tasks with respect to the letter grades are as follows.
Learning outcomes 1, 2 and 3:
P | Can formulate and convey most important points that could be expected on the topic. |
Cr / D | Can formulate and convey clearly all important points that could be expected on the topic. |
HD | As for Cr or D and can come up with novel insightful points on the topic. |
Learning Outcomes 4 and 5.
P | Be able to write a paper or document, or give a presentation, that would be acceptable at a conference. |
Cr / D | Be able to write a paper or document, or give a presentation, that would be well received at a conference. |
HD | Be able to write a paper or document, or give a presentation, that would be well received at a major international conference. |
These assessment standards will be used to calculate a numeric mark for each assessed task during marking.
The total raw mark for the unit will be calculated by summing up the marks for all assessment tasks according to the percentage weightings shown in the assessment summary.
The project report has a hurdle requirement in this unit: you will need to obtain at least 40% for the project report in order to pass the unit. If you obtain between 30% and 40% for the project report, then you will be given a second (and final) attempt to submit your report.
In order to pass the unit, you need a total raw mark of at least 50%.