AIML421 (2021) - Machine Learning Tools and Techniques
This course addresses the use of machine learning tools and techniques for analysing data and automatically generating applications. The course will explore a range of tools and techniques for classification, regression, image analysis, clustering, text mining, and preprocessing data. It examines the applicability and limitations of the techniques and methods for analysing and evaluating the outcome of using machine learning tools. Students will gain practical experience in applying a range of tools to a range of different problems from different domains.
Course learning objectives
Students who pass this course should be able to:
- Describe a range of standard machine learning problems, algorithms and techniques and discuss the applicability and limitations of the algorithms and techniques.
- Classify a particular problem, find possible ML algorithms or tools from a range of resources, and justify their selection of an appropriate tool to solve the problem.
- Prepare input data for a range of ML tools and apply the tools to the data in an appropriate way.
- Evaluate and report on the results of applying an ML tool to a problem.
The course is primarily offered in-person, but there will also be a remote option and there will be online alternatives for all the components of the course for students who cannot attend in-person.
Students taking this course remotely must have access to a computer with camera and microphone and a reliable high speed internet connection that will support real-time video plus audio connections and screen sharing. Students must be able to use Zoom; other communication applications may also be used. A mobile phone connection only is not considered sufficient. The computer must be adequate to support the programming required by the course: almost any modern windows, macintosh, or unix laptop or desktop computer will be sufficient, but an Android or IOS tablet will not.
If the assessment of the course includes tests, the tests will generally be run in-person on the Kelburn campus. There will be a remote option for students who cannot attend in-person and who have a strong justification (for example, being enrolled from overseas).
The remote test option will use Zoom for online supervision of the tests and you must be able to use Zoom with a camera, microphone, and screen-sharing. Students who will need to use the remote test option must contact the course coordinator in the first two weeks to get permission and make arrangements.
Withdrawal from Course
Withdrawal dates and process:
This course will be offered in-person and online. For students in Wellington, there will be a combination of in-person components and web/internet based resources. It will also be possible to take the course entirely online for those who cannot attend on campus, with all the components provided in-person also made available online.
The course will be taught by a combination of online content, in-person lectures (that will be recorded) and tutorials (during the lecture slots). Tutorials will be used to enable students to use the tools and techniques from the lectures and assignments. Online forums will be available to ask questions to tutors remotely and help desks will be available in-person. The assignments and project will allow students to explore and apply their knowledge to practical data problems, where working at home or in laboratories is permitted. The project will use in-person marking where possible, while all other assignments are submitted online and marked remotely. The project can be marked remotely where the onus is on the student to provide functioning code including the machine learning models.
This is the first time we have run the course so there is no feedback to report upon.
Dates (trimester, teaching & break dates)
- Teaching: 05 July 2021 - 08 October 2021
- Break: 16 August 2021 - 29 August 2021
- Study period: 11 October 2021 - 14 October 2021
- Exam period: 15 October 2021 - 06 November 2021
Set Texts and Recommended Readings
There are no required texts for this offering.
Mandatory Course Requirements
In addition to achieving an overall pass mark of at least 50%, students must:
- submit reasonable attempts for at least three of the four assignments, and
- submit a reasonable attempt at the final project.
If you believe that exceptional circumstances may prevent you from meeting the mandatory course requirements, contact the Course Coordinator for advice as soon as possible.
This course is internally assessed.
|Assessment Item||Due Date or Test Date||CLO(s)||Percentage|
|Assignment 1: Introduction to Machine Learning Problems, Tasks, and Techniques||week 5||CLO: 1,3||20%|
|Assignment 2: The Data Mining Process and Exploratory Data Analysis||Start of mid-term break||CLO: 1,2,3,4||12%|
|Assignment 3: Kaggle Competition||week 8||CLO: 2,3||20%|
|Assignment 4: Performance Evaluation and Optimisation||week 10||CLO: 1,4||12%|
|Capstone project (Code, scripts, and report on a solution to a problem)||Assessment period||CLO: 1,2,3,4||36%|
The penalty for assignments that are handed in late without prior arrangement (or use of "late days") is one grade reduction per day. Assignments that are more than one week late will not be marked.
There will be three late days automatically available across the assessment in the course. These will be automatically applied in the assessment system. These are intended to cover common reasons for short extensions, such as overlapping deadlines; technical difficulties; or unforeseen changes in personal circumstance.
Individual extensions beyond the three late days will only be granted in exceptional personal circumstances, and should be negotiated with the course coordinator before the deadline whenever possible. Documentation (eg, medical certificate) may be required.
Submission & Return
All work should be submitted through the ECS submission system, accessible through the course web pages. Marks and comments will be returned through the ECS marking system, also available through the course web pages.
Turnitin may be used to check for plagarism in written assessment.
Although the workload will vary from week to week, you should expect to spend approximately 10–12 hours per week on the course to give a total of 150 hours study time for the course.
Communication of Additional Information
All online material for this course can be accessed at https://ecs.wgtn.ac.nz/Courses/AIML421_2021T2/
Links to General Course Information
- Academic Integrity and Plagiarism: https://www.wgtn.ac.nz/students/study/exams/integrity-plagiarism
- Academic Progress: https://www.wgtn.ac.nz/students/study/progress/academic-progess (including restrictions and non-engagement)
- Dates and deadlines: https://www.wgtn.ac.nz/students/study/dates
- Grades: https://www.wgtn.ac.nz/students/study/progress/grades
- Special passes: Refer to the Assessment Handbook, at https://www.wgtn.ac.nz/documents/policy/staff-policy/assessment-handbook.pdf
- Statutes and policies, e.g. Student Conduct Statute: https://www.wgtn.ac.nz/about/governance/strategy
- Student support: https://www.wgtn.ac.nz/students/support
- Students with disabilities: https://www.wgtn.ac.nz/st_services/disability/
- Student Charter: https://www.wgtn.ac.nz/learning-teaching/learning-partnerships/student-charter
- Terms and Conditions: https://www.wgtn.ac.nz/study/apply-enrol/terms-conditions/student-contract
- Turnitin: http://www.cad.vuw.ac.nz/wiki/index.php/Turnitin
- University structure: https://www.wgtn.ac.nz/about/governance/structure
- VUWSA: http://www.vuwsa.org.nz
Offering CRN: 33066
Prerequisites: 60 300-level COMP, DATA, NWEN, STAT or SWEN pts
Restrictions: COMP 309
Duration: 05 July 2021 - 07 November 2021
Starts: Trimester 2