ECE6179 · Neural networks and deep learning

Overview

This unit introduces fundamentals of deep learning and how it can solve problems in many areas such as image classification, filter design and natural language processing. Neural networks are first described and how training can be achieved with backpropagation. Various forms of deep neural networks are developed such as multilayer perceptrons, convolution neural networks and recurrent neural networks. Deep reinforcement learning is discussed. The mathematics of stochastic optimisation is used to interpret and understand the behaviour and training of these networks. Programming approaches are discussed for training and deploying neural networks. Deep learning technologies and design examples are discussed in areas such as robotics, driverless cars, personal cognitive assistants and mastering of games such as GO.

Offerings

Assessment

The Handbook lists an examination for this unit.

Continuous assessment: 50% Final assessment: 50% Final grades: PGO (pass grade only) or NGO (fail)

Assessment details may change. Please refer to the assessment information in Moodle closer to the start of the teaching period.

Requisites

Learning outcomes

1. Describe concepts and fundamentals of deep learning such as the backpropagation algorithm and adversarial learning.
2. Appraise various forms of deep neural networks such as multilayer perceptrons, convolution neural networks and recurrent neural networks.
3. Interpret and apply the mathematics of deep learning such as stochastic optimisation.
4. Design deep learning solutions to problems in computer vision, natural language processing and signal processing. Examples are image classification, object detection, sequence modelling and filter design.
5. Design and synthesise the training and deployment of neural networks using a high-level programming language.
6. Critically assess sources of information and contents of scientific publications and choose relevant information

Workload

The minimum total expected workload to achieve the learning outcomes for this unit is 144 hours per semester typically comprising a mixture of 3-6 hours of scheduled learning activities and 6-9 hours of independent study per week. Scheduled activities may include a combination of teacher-directed learning, peer-directed learning and online engagement. Independent study may include associated readings, assessment and preparation for scheduled activities.

Student experience, not official rules. Nothing here changes what the Handbook says.