This paper exposes students to selected machine learning algorithms and includes assignments that require the implementation of these algorithms.

The learning outcomes for this paper are linked to Washington Accord graduate attributes WA1-WA11. Explanation of the graduate attributes can be found at: https://www.ieagreements.org/

The understanding of theoretical concepts concerning machine learning algorithms will be assessed in two closed-book, in-class tests. The first test will cover the material discussed in the first half of the lectures. The second test will cover the material from the remaining lectures.

The ability to turn understanding of machine learning algorithms into working code will be assessed in two assignments. In each of the two assignments, a machine learning algorithm from a scientific publication will be chosen by the lecturer to be implemented as individual work by each student. Part of the assignment will be an evaluation of the student's algorithm implementation on benchmark datasets. An assignment report describing the algorithm and the benchmark results obtained, along with the submitted source code, will be used to determine the grade for each assignment.

Samples of your work may be required as part of the Engineering New Zealand accreditation process for BE(Hons) degrees. Any samples taken will have the student name and ID redacted. If you do not want samples of your work collected then please email the engineering administrator, Natalie Shaw (natalie.shaw@waikato.ac.nz), to opt out.

Students should expect to spend 10 hours per week on this paper, made up of 2 hours of lectures, and (on average) 8 hours spent working on the assignments and revising lecture notes.