Machine Learning in Science (Taught)

The development and use of machine learning (ML) and artificial intelligence (AI) have revolutionised areas such as computer vision, speech recognition and language processing.

On this course you will learn how to apply ML and AI techniques to real scientific problems. This will help you build vital skills, enhancing your employability in a rapidly expanding area.

Graduates of this course will learn how to:

identify and use relevant computational tools and programming techniques
apply statistical and physical principles to break down algorithms, and explain how they work
design strategies for applying machine learning to the analysis of scientific data sets.
In addition, you will develop a broad set of transferable skills, including communication, critical thinking, and problem-solving. Previous students of this course have undertaken paid part-time internships with external partners.

Find out what our graduates say about the course on our Physics Blog.

You will have the opportunity to develop your own research project on a topic of your choice. Previous projects have looked at:

Deep Learning for drug discovery
Machine Learning for sustainable solvent selection
Quantum reinforcement learning
Supervised machine learning on a quantum computer
Deep Learning network for fatigue monitoring of wind turbine blades
Shaking all over – vibration cancellation at the atomic level
Using machine learning to automatically segment the placenta from pregnancy MRI scans
Machine learning assisted high-throughput computational screening of metal organic frameworks for biogas upgrading
Simulating the Universe
Detecting dark matter substructure in galaxies
Personalised modelling of cerebral blood flow from multi-modal features for early detection of dementia
Machine Learning natural product biosynthesis
Advanced natural language processing in Fintech