Overview
MATH5881 is a New Honours and Postgraduate coursework course.
Units of credit: 6
Cycle of offering: Term 2
Graduate attributes: The course will enhance your research, inquiry and analytical thinking abilities.
Course Information
This course gives students a statistical and mathematical perspective on modern machine learning methods, with the aim of obtaining a deeper understanding of how such methods work and have been derived. This theoretical knowledge will then be used to demonstrate how to fine tune machine learning methods for complex applications. This course will focus on principles of neural networks (convolutional, recurrent, sequential methods), optimisation methods relevant for machine learning and generative AI (autoencoders, diffusion models, generative adversarial networks).
The course outline will be made available closer to the start of term - please visit this website: www.unsw.edu.au/course-outlines
The course outline also contains information about course objectives, assessment, course materials and the syllabus.
UNSW Plagiarism Policy
The University requires all students to be aware of its policy on plagiarism.
For courses convened by the School of Mathematics and Statistics no assistance using generative AI software is allowed unless specifically referred to in the individual assessment tasks.
If its use is detected in the no assistance case, it will be regarded as serious academic misconduct and subject to the standard penalties, which may include 00FL, suspension and exclusion.
The Online Handbook entry contains contains information about the course. (The timetable is only up-to-date if the course is being offered this year.)
If you are currently enrolled in MATH5881, you can log into UNSW Moodle for this course.
Course Information
This course gives students a statistical and mathematical perspective on modern machine learning methods, with the aim of obtaining a deeper understanding of how such methods work and have been derived. This theoretical knowledge will then be used to demonstrate how to fine tune machine learning methods for complex applications. This course will focus on principles of neural networks (convolutional, recurrent, sequential methods), optimisation methods relevant for machine learning and generative AI (autoencoders, diffusion models, generative adversarial networks).
This course is intended as an elective for Statistics majors & minors, Quantitative Data Science Major and Mathematics majors, both at the at Postgraduate level. Prior knowledge of basic probability is necessary, and knowledge of stochastic processes will be advantageous but is not required. This course complements MATH5191 Optimisation for data science by focusing on various neural network architectures and training methods that make use of some optimisation methods explored in MATH5191, along with probabilistic aspects governing generative modelling. Additionally, this course focuses on mathematical and statistical foundations of many machine learning methods discussed from a computational perspective in MATH5836