COMP6242

Deep Learning

Credit
6 units
Catalogue year
2027
Recorded offerings
First Semester

Course information

The course covers the theory and practice of deep learning. Students will learn the foundational mathematics behind deep learning and explore topics such as multi-layer perceptrons (MLPs), back-propagation and automatic differentiation, convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformers, generative models, and the role of data in training models. These techniques play a crucial role in modern AI systems, including image and video understanding, natural language processing, generative AI, robotics, medicine and scientific discovery. The various practical assessments will enhance student's understanding and intuition of deep learning and its application.

Requisite and Incompatibility

To enrol in this course you must have successfully completed: (COMP3670 or COMP6670 or COMP8410) AND (COMP1110 or COMP6710 or COMP7710 or COMP1730 or COMP6730).

Learning Outcomes

Upon successful completion, students will have the knowledge and skills to:

Describe and apply the theory of artificial neural networks and the universal approximation theorem.

Apply the theory of training a convolutional neural network or transformer model.

Write programs to design, train and test neural networks to solve problems in a given application area.

Competently apply programming and software tools to write programs to solve realistic problems using deep neural networks.

Understand the principals of testing and evaluating the performance of deep neural networks, and apply these principles in practice.

Understand the role of data in training deep learning systems including ethical considerations and potential biases.

Research an application area and apply deep neural network methods to a problem in that area.

Saved ANU Programs & Courses information, 2027. Future offerings are indicative. Checks use the saved requirements and your fictional academic record.

Saved requirements encoded for automatic checks. See your requirement checks for what can be decided.

Course library: sources, offering dates and related entries

Read the full published course information ↗

Who reviews permission requests?

Dr Mara Quinn is the fictional reviewer assigned to COMP6242 in this prototype. The selected course determines where a request goes.

Make this part of your semester

Sign in to check your fictional academic record, save this offering, and request permission if needed.

Sign in