Deep Learning and Generative AI

• Credit value: 30 credits at Level 6
• Convenor: Professor George Magoulas
• Assessment: a mini-project (40%) and two-hour open-book examination (60%)

In this module you will develop advanced knowledge and skills in deep neural networks and models used in generative AI. The module provides an opportunity to develop an in-depth understanding of cutting-edge AI techniques through the exploration of convolutional neural networks, recurrent neural networks, GANs and transformers. You will undertake practical lab tasks using real-world datasets and state-of-the-art AI tools and explore applications areas including natural language and media creation.

Indicative syllabus

• Introduction to deep learning
• Neural network architectures
• Training deep neural networks
• Convolutional neural networks
• Recurrent neural networks
• Generative adversarial networks
• Transformers and attention mechanisms
• Autoencoders and variational autoencoders
• Ethics in AI
• Practical applications

By the end of this module you will be able to:

• utilise fundamental concepts and techniques in deep learning and generative AI
• apply neural network architectures such as convolutional neural networks and recurrent neural networks to solve complex problems
• evaluate the performance of generative models such as generative adversarial networks and transformers in various applications
• understand the ethical implications and potential biases in AI applications
• analyse complex datasets and develop solutions using deep learning techniques
• critically evaluate the effectiveness of different AI models in generating realistic data
• formulate and test hypotheses related to deep learning and generative AI
• synthesise knowledge from computer science, mathematics and AI to solve problems
• implement deep learning algorithms using programming frameworks such as TensorFlow and PyTorch
• use specialised AI tools to develop and train generative models
• develop and deploy AI applications for tasks such as image generation, natural language
• processing and autonomous systems
• conduct investigations and analyse results to improve AI models.