Gain insights into the different types of problems that exist in machine learning and the basic algorithms used to address them.

Understand the fundamentals of Python and learn how to write procedural, object-oriented and functional programs in Python.

Learn how to apply knowledge of domain properties and agent architectures in the representation of problems in symbolic AI.

Explore the issues and implications around ethics and philosphical problems, fairness and bias, and justifiable explanations in AI decision-making.

Obtain practical experience in developing AI applications and using software engineering techniques in the design and implementation of large programs.

Explore how images are formed, how they are represented on computers and how they can be processed by computers to extract semantic information.

Learn how to describe the core principles of autonomous systems learning and calculate mathematical solutions to problems using reinforcement learning theory.

Develop a deeper understanding of optimal decision making models, algorithms and applications to engineering, finance, and machine learning.

Learn how to design and implement modern statistical machine learning methodologies, as well as inference mechanisms.

Develop intellectual and practical skills in the use of modal logics for knowledge representation and automated reasoning in artificial intelligence.

Gain an in-depth understanding of logic-based learning, starting from its key foundation concepts and principles before moving to more recent advances.

Explore the fundamental concepts and advanced methodologies of deep learning and relate them to real-world problems.

Discover why knowledge representation and reasoning are essential components of an intelligent system and are at the core of artificial intelligence research.

Examine how probability can be used to make decisions by a computer and advance your understanding of inference networks and linear and non-linear methods in statistical pattern recognition.

Explore the fundamental concepts and advanced methodologies of machine learning for imaging and relate them to real-world problems in computer vision and medical image analysis. 

Acquire the techniques and tools needed to devise and develop natural language processing (NLP) components and applications.

Engage with the emerging field of robot learning and discover how robots can acquire skills and control their bodies using machine learning techniques.

Assess the exciting field of mobile robotics, at a time when cutting-edge robots are beginning to leave the research laboratory to tackle real-world tasks.

Explore applications of artificial intelligence technologies that will improve or transform existing financial, health and other systems.

Understand the rationale behind the theoretical end of computational neuroscience and basic principles of the tools needed to simulate the brain's intelligent behaviour in this interdisciplinary module.

Gain a flavour of different aspects of the broad and ever-expanding field of graph theory and learning, including conventional graph data analysis methods and the nascent field of graph neural networks.

Explore the intersection of robotics and human-computer interaction, covering user-centric and user study design, data analysis, and relevant theoretical foundations, in this exciting new field.

Implement and operate a simplified machine learning-based system in this module covering engineering concepts underpinning trustworthy systems. Looks at all aspects of systems, including data ingestion, user experience, regulation and wider society.

Understand the basic concepts of quantitative finance and financial engineering and build awareness of the major decision, hedging, and pricing problems in finance.

Analyse the foundational principles behind decentralised ledgers and apply them to current research in cryptocurrencies.

Discover the basic notions of quantum computing and be introduced to Quantum Bits, Quantum Entanglement and Quantum Algorithms.

Delve into the deep connections between information theory, statistics and machine learning, in this module linking computing, statistics and geometry. Includes mathematical and computational exercises, and provides crucial theoretical background for a career in data science or machine learning.