Skip to main content
Unit of study_

COMP5329: Deep Learning

This course provides an introduction to deep machine learning, which is rapidly emerging as one of the most successful and widely applicable set of techniques across a range of applications. Students taking this course will be exposed to cutting-edge research in machine learning, starting from theories, models, and algorithms, to implementation and recent progress of deep learning. Specific topics include: classical architectures of deep neural network, optimization techniques for training deep neural networks, theoretical understanding of deep learning, and diverse applications of deep learning in computer vision.

Code COMP5329
Academic unit Computer Science
Credit points 6
Prerequisites:
? 
None
Corequisites:
? 
None
Prohibitions:
? 
None
Assumed knowledge:
? 
COMP5318

At the completion of this unit, you should be able to:

  • LO1. demonstrate knowledge of the broad range of deep learning applications, such as image classification, object detection, image segmentation and face recognition
  • LO2. use deep learning software to create deep learning prototypes
  • LO3. evaluate deep learning algorithms
  • LO4. demonstrate knowledge of the main methods of deep neural network design and evaluation and the relative strengths and weaknesses of each, and their most appropriate uses
  • LO5. model application problems as deep learning problems
  • LO6. apply and tailor known deep learning algorithms for solving new challenging problems
  • LO7. present the design and evaluation of a deep learning prototype, defining the requirements, describing the design processes and evaluation.

Unit outlines

Unit outlines will be available 2 weeks before the first day of teaching for 1000-level and 5000-level units, or one week before the first day of teaching for all other units.

There are no unit outlines available online for previous years.