FIT3191 · Generative artificial intelligence

Overview

This unit covers the theoretical and practical foundations of Generative Artificial Intelligence (GenAI), building on prior knowledge of deep learning. The unit begins with essential Natural Language Processing (NLP) concepts that underpin modern generative systems, such as text representation, contextual embeddings, and sequence modelling. You then progress to large language models (LLMs), advanced generative techniques including variational autoencoders (VAEs), generative adversarial networks (GANs), and diffusion models, as well as their integration into real-world applications such as conversational systems, summarisation, translation, and multimodal AI. Throughout the unit, you will critically evaluate the architectures and training strategies that power generative systems, with strong emphasis on ethical, societal, and regulatory considerations. By the end of the unit, you will be able to design, apply, and evaluate generative AI solutions responsibly across various complex domains.

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. Explain the core principles of NLP and Generative AI, and how these methods enable artificial intelligence systems to interpret and generate human language.
2. Analyse the architectures and training strategies that underpin large language models and other generative approaches.
3. Apply NLP and Generative AI in practical applications such as dialogue systems, translation, summarisation, and multimodal systems.
4. Evaluate generative models using theoretical foundations and appropriate metrics, considering accuracy, creativity, robustness, and limitations.
5. Assess the ethical, legal, and societal implications of NLP and generative AI technologies, including bias, fairness, safety, and governance.

Workload

No workload detail published.

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