Introductory description

This module provides an intensive, applied approach to advanced Deep Learning (DL), prioritising the hands-on engineering of neural architectures to solve complex, real-world challenges. Rather than focusing solely on theoretical abstractions, students will engage directly with practical deployment scenarios, such as building applications or optimising models in computer vision, natural language processing, or other areas. Students will investigate foundational principles and architectures, comparing traditional machine learning with deep learning approaches while critically engaging with real-world use cases. Students will have the opportunity to develop algorithms to solve real-world problems, building the skills needed to design, implement, and evaluate AI systems. The module combines theoretical knowledge with hands-on experience to prepare students for both research and applied roles in the field of AI.

Module aims

Outline syllabus

This is an indicative module outline only to give an indication of the sort of topics that may be covered. Actual sessions held may differ.

• Foundations of Artificial Intelligence and Deep Learning: Deep Learning Overview; Deep Learning vs Traditional Learning; Introduction of Ethical and Societal Implications; Emerging Trends; and Overview of Model Interpretability and Explainability (XAI).

• Foundations of Neural Networks: Perceptron; Backpropagation; Activation and Loss Functions; Hyperparameters; Model Evaluation and Comparison.

• Deep Learning Architectures and Applications: Model Deployment and Comparison (e.g., CNN, RNN, LSTM, Variational Autoencoders, or Generative Adversarial Networks (GANs)) for different applications, such as image or text analysis;

Learning outcomes

By the end of the module, students should be able to:

• Critically evaluate and explain the key differences between traditional machine learning and deep learning approaches.
• Critically evaluate deep learning and artificial intelligence solutions and their implications.
• Demonstrate an understanding of emerging trends and research development in AI.
• Design and evaluate deep learning models for practical applications.
• Collaborate effectively as part of a group to develop and communicate a practical AI solution by presenting findings through reproducible code, visualisations, or technical reporting.

Indicative reading list

Reading lists can be found in Talis

Specific reading list for the module

Interdisciplinary

In particular, combining computer science and mathematics/statistics

Subject specific skills

• Ability to evaluate Artificial Intelligence and Deep Learning techniques.

• Design and implementation of deep learning models.

• Model evaluation and performance analysis, including the use of appropriate metrics, validation techniques, and comparative analysis.

• Understanding and critical appraisal of current research trends.

• Working with AI model pipelines, including data preprocessing, fine-tuning, testing, and reporting.

• Ability to use Python Libraries and Frameworks to implement Deep Learning applications.

Transferable skills

• Critical thinking and analytical reasoning.

• Problem-solving in complex and uncertain environments, with an emphasis on practical experimentation and iteration.

• Collaboration and teamwork.

• Effective technical communication.

• Independent learning and self-direction.

• Time and project management.

• Adaptability and digital literacy.