COSC401-25S1 (C) Semester One 2025

Machine Learning

15 points

Details:
Start Date: Monday, 17 February 2025
End Date: Sunday, 22 June 2025
Withdrawal Dates
Last Day to withdraw from this course:
  • Without financial penalty (full fee refund): Sunday, 2 March 2025
  • Without academic penalty (including no fee refund): Sunday, 11 May 2025

Description

A study of computational processes that underlie learning in machines. The course covers fundamental theories and algorithms in machine learning.

Covid-19 Update: Please refer to the course page on AKO | Learn for all information about your course, including lectures, labs, tutorials and assessments.

In order to complete the course successfully, students should be familiar with:

- basic linear algebra (operations on vectors and matrices, inverse matrices, eigen-values/vectors, vector geometry, etc);
- basic calculus (limits, differentiation and integration and their applications, partial derivatives, chain rule, etc);
- basic probability (marginal and conditional probabilities, discrete and continuous random variables, expectation, etc); and
- basic logic and set theory.

Machine Learning is the study of how computer programs can improve their performance automatically through experience, or "learn from experience". At the end of this course you will have a broad overview of this rapidly growing area. You will also be able to critically assess the potential of various Machine Learning paradigms and techniques.

The course covers major paradigms of learning including supervised, unsupervised, and reinforcement learning. Some of the topics discussed include:

- Learning theory
- Decision trees
- Linear models
- Kernels and Support Vector Machines
- Probabilistic models (parametric and non-parametric methods)
- Graphical models, neural networks, and deep learning
- Reinforcement learning
- Ensemble learning
- Unsupervised learning

Learning Outcomes

1. Develop a thorough understanding of the theoretical foundations underpinning machine learning algorithms [WA2]
2. Analyse the mathematical models that form the basis of machine learning algorithms, with a focus on their assumptions, limitations, and areas of application [A3, WA4, WA5]
3. Implement machine learning algorithms from scratch, focusing on the nuances of algorithmic design, optimisation techniques, and parameter tuning to deepen practical understanding [WA3, WA4, WA5]
4. Evaluate the performance of machine learning models using appropriate metrics and validation techniques, with an emphasis on understanding the trade-offs between model complexity and generalisation capability [WA4, WA5]
5. Understand and implement key machine learning concepts and techniques, such as feature space transformations, kernel methods, and representation learning, while also exploring strategies across supervised, unsupervised, ensemble, and reinforcement learning [WA3, WA4, WA10]

University Graduate Attributes

This course will provide students with an opportunity to develop the Graduate Attributes specified below:

Employable, innovative and enterprising

Students will develop key skills and attributes sought by employers that can be used in a range of applications.

Prerequisites

(i) COSC367; and (ii) At least 45 points of MATH/EMTH/STAT (but not including MATH101, MATH110, EMTH117, STAT101); and (iii) Subject to approval by the Head of Department

Timetable 2025

Students must attend one activity from each section.

Lecture A
Activity Day Time Location Weeks
01 Wednesday 10:00 - 12:00 E6 Lecture Theatre
17 Feb - 6 Apr
28 Apr - 1 Jun

Timetable Note

Please note that the course activity times advertised here are currently in draft form, to be finalised at the end of January for S1 and whole year courses, and at the end of June for S2 courses.

Please hold off enquiries about these times until those finalisation dates.

Course Coordinator

Kourosh Neshatian

Assessment

Assessment Due Date Percentage  Description
Assignments 30% On quiz server.
Test 15%
Final Exam 55%


Covid-19 Update: Please refer to the course page on AKO | Learn for all information about your course, including lectures, labs, tutorials and assessments.

Textbooks / Resources

Recommended Reading

Bishop, Christopher M; Pattern recognition and machine learning ; Springer, 2006.

Mitchell, Tom M.1951-; Machine Learning ; McGraw-Hill, 1997.

Shalev-Shwartz, Shai. , Ben-David, Shai; Understanding machine learning :from theory to algorithms ; Cambridge University Press, 2014.

Witten, I. H. , Frank, Eibe., Hall, Mark A; Data mining : practical machine learning tools and techniques ; 3rd ed; Morgan Kaufmann, 2011.

Additional Course Outline Information

Grade moderation

The Computer Science department's grading policy states that in order to pass a course you must meet two requirements:
1. You must achieve an average grade of at least 50% over all assessment items.
2. You must achieve an average mark of at least 45% on invigilated assessment items.

If you satisfy both these criteria, your grade will be determined by the following University-wide scale for converting marks to grades: an average mark of 50% is sufficient for a C- grade, an average mark of 55% earns a C grade, 60% earns a C+ grade and so forth. However if you do not satisfy both the passing criteria you will be given either a D or E grade depending on marks. Marks are sometimes scaled to achieve consistency between courses from year to year.

Students may apply for special consideration if their performance in an assessment is affected by extenuating circumstances beyond their control.

Applications for special consideration should be submitted via the Examinations Office website within five days of the assessment.

Where an extension may be granted for an assessment, this will be decided by direct application to the Department and an application to the Examinations Office may not be required.

Special consideration is not available for items worth less than 10% of the course.

Students prevented by extenuating circumstances from completing the course after the final date for withdrawing, may apply for special consideration for late discontinuation of the course. Applications must be submitted to the Examinations Office within five days of the end of the main examination period for the semester.

Indicative Fees

Domestic fee $1,176.00

* All fees are inclusive of NZ GST or any equivalent overseas tax, and do not include any programme level discount or additional course-related expenses.

For further information see Computer Science and Software Engineering .

All COSC401 Occurrences

  • COSC401-25S1 (C) Semester One 2025