ECE4179 · Neural networks and deep learning

Overview

This unit introduces the fundamentals of deep learning and its applications across various domains, including image classification, signal processing, and natural language understanding. Neural networks are first described, followed by how training can be achieved with backpropagation. Various forms of deep neural networks are developed, including Multilayer Perceptrons (MLPs), Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs). Modern advancements such as transformers and Large Language Models (LLMs) are described, as well as their deployment and fine-tuning. The mathematics of optimisation and generalisation is used to interpret and understand the behaviour and training of these networks. Programming frameworks for training, fine-tuning, and deploying neural networks are discussed. Deep learning technologies and design examples are discussed in areas such as visual perception, driverless cars, intelligent assistants, and generative AI.

Areas of study: E3001 Bachelor of Engineering (Honours) - Specialisation: Biomedical engineering E3001 Bachelor of Engineering (Honours) - Specialisation: Robotics and mechatronics engineering Minor: Internet of Things (IoT) Minor: Artificial intelligence in engineering

Offerings

Assessment

The Handbook lists an examination for this unit.

Semester 1: Continuous assessment: 40% Final assessment: 60% Semester 2: Continuous assessment: 50% Final assessment: 50%

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. Discern and appreciate 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. Demonstrate the training and deployment of neural networks using a high level programming language.
6. Appraise critically the 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.