FIT2112 · Deep learning

Overview

Deep learning (DL) has been a driving force behind modern Artificial Intelligence. The remarkable success of DL in various applications has garnered significant attention and made it a highly sought-after skill across numerous industries. This unit will provide you with a comprehensive understanding of deep learning theory within the broader context of machine learning. Additionally, you will acquire practical skills to apply DL to real-world applications across a range of AI cognitive tasks, such as image and object recognition in computer vision and text classification using deep neural embeddings. The learning activities will focus on fundamental DL concepts, including neural networks (NN), convolutional NN, backpropagation, optimisation for deep learning, adversarial robustness, attention mechanism and transformers.

Offerings

The Handbook publishes no offerings for this unit.

Assessment

The Handbook publishes no assessment items for this unit yet.

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 basic and advanced concepts of deep learning;
2. Analyse what makes deep learning work or fail, and critique where it should be applied;
3. Explain the fundamental elements of deep learning;
4. Construct deep neural networks, convolutional NNs, RNNs, and Transformers and apply different strategies for training them.

Workload

No workload detail published.

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