EGB250 Machine Learning for Engineering II

This unit will introduce deep learning methods, which form the foundation of most modern large-scale machine learning systems. The unit will introduce key concepts and architectures including convolutional and recurrent neural networks, and different training approaches that can be applied to deep neural networks. These methods will be explored through a number of engineering applications and case studies to understand the capabilities of the different methods, and when each may be appropriate. The unit makes use of python, jupyterlab, git and state of the art machine learning libraries. Applications and case-studies will draw from a variety of engineering disciplines, with a focus on signal data including images, audio, and biomedical data.

Unit information

Unit code: EGB250
Faculty: Faculty of Engineering
School/Discipline: School of Electrical Engineering and Robotics
Study area: Engineering
Credit points: 12

Dates and locations

Teaching period	Dates	Locations
Semester 1, 2028	21 February 2028 - 17 June 2028	Gardens Point

See all available class timetables for this unit

Previous study requirements

Prerequisites: EGB150
Anti-requisites: CAB420

Guide to previous study requirements

Prerequisites: To enrol in this unit, you must have completed these prerequisite units (or have credit, advanced standing or exemption for them), or be able to demonstrate that you have equivalent background knowledge.
Anti-requisites: You can’t enrol in this unit if you have completed any of these anti-requisite units.
Co-requisites: To enrol in this unit, you must have already completed these co-requisite units, or you must enrol in them at the same time.
Equivalents: You can’t enrol in this unit if you have completed any of these equivalent units.
Assumed knowledge: We assume that you have a minimum level of knowledge in certain areas before you start this unit.

Unit outlines

Loading unit outlines...

Offer of some units is subject to viability, and information in these Unit Outlines is subject to change prior to commencement of the teaching period.