Unit Outline

The aim of this unit is to provide students with the foundation knowledge and understanding of Machine Learning and its applications in various domains including computer vision, data analytics and text mining. This unit will equip students with essential knowledge that is needed for developing smart software applications by using machine learning algorithms and tools.

Intended Learning Outcomes

As per the Assessment and Results Policy 1.3, your results will reflect your achievement against specified learning outcomes.

On completion of this unit, you will be able to:


1	Explain concepts of different categories of machine learning methods
2	Apply suitable tools and techniques to develop machine learning methods to solve practical problems.
3	Evaluate machine learning solutions toward characteristics of practical problems

Requisites


REQUISITE TYPE	REQUISITES
Pre-requisite	KIT205 OR KIT206

Alterations as a result of student feedback

Nil

Teaching arrangements


ATTENDANCE MODE	TEACHING TYPE	LEARNING ACTIVITY	CONTACT HOURS	FREQUENCY
On Campus	Workshop	A structured real-time (i.e. synchronous) activity that involves a mix of presentation of new information/ideas/skills and guided activities related to that information/ideas/skills. All students are expected to attend.	2	Weekly
	Independent Learning	Involving reading, listening to audio, watching video, and/or completing exercises and/or quizzes, self-study is individual work undertaken when the student chooses (i.e. asynchronous), most likely through engagement with MyLO. The content is examinable, and may need to be completed prior to attending classes and/or attempting assessment tasks.	1	Weekly
	Tutorial	A structured real-time (i.e. synchronous) activity in a small-group setting where the primary purpose is the clarification, exploration or reinforcement of subject content presented or accessed at another time or place (e.g. lecture, preparatory work). It is reliant on student-teacher and student-student interaction and dialogue for achievement of its learning outcomes. The students enrolled in the tutorial are expected to attend.	2	Weekly

Attendance/Engagement Expectations

It is expected that you will attend all on-campus and onsite learning activities. This is to support your own learning and the development of a learning community within the unit.

If you miss a learning activity for a legitimate reason (e.g., illness, family commitments) teaching staff will attempt to provide alternative activities (e.g., make up readings) where it is possible.

If you are unable to attend regularly, please discuss the situation with your course coordinator and/or our UConnect support team.

How will I be Assessed?

Assessment schedule


ASSESSMENT TASK #	ASSESSMENT TASK NAME	DATE DUE	WEIGHT	LINKS TO INTENDED LEARNING OUTCOMES
ASSESSMENT TASK 1:	Assignment 1	Week 10	40 %	LO1, LO2
ASSESSMENT TASK 2:	Assignment 2	Week 13	30 %	LO1, LO2, LO3
ASSESSMENT TASK 3:	Lab Exercises	Refer to Assessment Description	30 %	LO1, LO2, LO3

Assessment details

Assessment Task 1: Assignment 1

TASK DESCRIPTION:

For your major project you will apply deep learning techniques to a specific dataset or problem.
Dataset, or training environment, preparation is crucial for deep learning and can be very time consuming. Similarly developing new techniques or applying techniques in novel ways takes many hours of planning and development time. You will not be able to achieve both in the time available.
To achieve the ILOs associated with this assignment, you should either:
• Develop/acquire, and process a novel dataset (or training environment for reinforcement learning), and demonstrate the application of a standard deep learning technique to this dataset/environment
• Take an existing machine learning dataset or machine learning environment and develop a novel deep learning architecture or method that achieves better performance than a standard implementation on that dataset.
• The two guest lecturers will also provide two projects. You can also select the projects provided by them. Detailed information about the 2 projects will be introduced in the guest lectures.

TASK LENGTH:

Required source code, datasets and associated laboratory notes.

DUE DATE:

Week 10

WEIGHT:

40 %

CRITERION #

CRITERION

MEASURES INTENDED LEARNING OUTCOME


1	Develop and prepare a dataset or reinforcement learning environment for deep learning	LO1, LO2
2	Develop a deep learning solution	LO2

Assessment Task 2: Assignment 2

TASK DESCRIPTION:

For your major project you implemented a deep learning technique for a specific dataset or problem.
For this assignment you will thoroughly test your implementation and write an academic report covering your findings.
You will use the Springer LNAI template. The report should be at most 8 pages long.
The template is in LaTeX and you should use a Latex editor to prepare your report. Your report should be no more than 8 pages and should contain (at least) the following sections:
• Abstract
• Background
• Methodology
• Results and Discussion
• Conclusion
• References

TASK LENGTH:

You will use the Springer LNAI template. The report should be at most 8 pages long

DUE DATE:

Week 13

WEIGHT:

30 %

CRITERION #

CRITERION

MEASURES INTENDED LEARNING OUTCOME


1	Write a report that adheres to academic norms	LO1
2	Provide a background and introduction for the topic of your project	LO2
3	Describe your methodology	LO3
4	Present results and draw conclusions	LO1, LO2, LO3

Assessment Task 3: Lab Exercises

TASK DESCRIPTION:

In this unit you will have fortnightly lab exercises where you will be conducting experiments and investigations. In machine learning research it is extremely important that you keep detailed records of experiments so that in future you can reproduce results if necessary. Also, some trials will take a long time to complete, having to repeat a trial because you lost the data can be incredibly frustration.

To encourage you to keep good records, your lab notebook will be assessed at the end of each lab exercise. You will get a mark out of 5 for each exercise based on clarity and completeness.

Since a lot of the entries will be numerical records, you will be using Excel for your notebook. You should create a new Excel sheet for each exercise. At a minimum, each sheet should have:
• A Title
• An overview of the work completed
• One or more experimental records
• Very detailed setup information
• Detailed records (including records for failed or restarted trials)
• Analysis of results
• Summary and future work (things you would like to try when you have more time)

Before you leave each exercise, make sure that your tutor checks your lab notebook and your completeness.

TASK LENGTH:

1 Work Sheet per lab exercise

DUE DATE:

Refer to Assessment Description

WEIGHT:

30 %

CRITERION #

CRITERION

MEASURES INTENDED LEARNING OUTCOME


1	Documented machine learning exercise in lab notebook using required format	LO1
2	Completed lab task using required tools and techniques	LO2, LO3

How your final result is determined

To pass this unit, you need to demonstrate your attainment of each of the Intended Learning Outcomes, achieve a final unit grade of 50% or greater, and pass any hurdle tasks.

Submission of assignments

Where practicable, assignments should be submitted to an assignment submission folder in MYLO. You must submit assignments by the due date or receive a penalty (unless an extension of time has been approved by the Unit Coordinator). Students submitting any assignment in hard copy, or because of a practicum finalisation, must attach a student cover sheet and signed declaration for the submission to be accepted for marking.

Requests for extensions

If you are unable to submit an assessment task by the due date, you should apply for an extension.

A request for an extension should first be discussed with your Unit Coordinator or teaching support team where possible. A request for an extension must be submitted by the assessment due date, except where you can provide evidence it was not possible to do so. Typically, an application for an extension will be supported by documentary evidence: however, where it is not possible for you to provide evidence please contact your Unit Coordinator.

The Unit Coordinator must notify you of the outcome of an extension request within 3 working days of receiving the request.

Late Penalties

Assignments submitted after the deadline will receive a late penalty of 5% of the original available mark for each calendar day (or part day) that the assignment is late. Late submissions will not be accepted more than 10 calendar days after the due date, or after assignments have been returned to other students on a scheduled date, whichever occurs first. Further information on Late Penalties can be found on the Assessments and Results Procedure.

Review of results and appeals

You are entitled to ask for a review of the marking and grading of your assessment task if there is an irregularity in the marking standards or an error in the process for determining the outcome of an assessment. Details on how to request a review of a mark for an assignment are outlined in the Review and Appeal of Academic Decisions Procedure.