Machine Learning in Science - Project
| Code | School | Level | Credits | Semesters |
| PHYS4037 | Physics and Astronomy | 4 | 60 | Summer UK |
- Code
- PHYS4037
- School
- Physics and Astronomy
- Level
- 4
- Credits
- 60
- Semesters
- Summer UK
Summary
In this module a substantial investigation will be carried out in the form of a research project on the application of the machine learning techniques learned as part of the MLiS MSc to a scientific problem. The study will be largely self-directed, with oversight and input provided where necessary by a supervisor from the School of Physics and Astronomy, School of Computer Science or School of Mathematical Sciences. The topic will be chosen from a list of potential projects provided by the Schools in the Faculty of Science. The topic could be based on a theoretical and/or computational investigation, a review of research literature, and/or a combination of the two.
Target Students
Only available to students doing the Machine Learning in Science MSc
Co-requisites
Modules you must take in the same academic year, or have taken in a previous year, to enrol in this module:
Assessment
- 100% REPORT: A substantial word-processed report
Assessed by end of summer vacation
Educational Aims
The purpose of this module is to broaden and deepen the students' knowledge and understanding of modern methods of ML and AI and how they can be applied to a novel problem originating from the sciences. This will be achieved by carrying out a detailed and substantial investigation into one specific scientific problem requiring ML/AI for its elucidation.Learning Outcomes
A student who completes this course successfully should be able to:
L1 - apply the techniques of machine learning to study a problem originating from one of the sciences;
L2 - programme a functioning neural network to perform supervised learning , unsupervised learning, or reinforcement learning, or a combination of these suited to the scientific problem being studied, performing the necessary numerical and analytical computations;
L3 - search and review relevant literature and other resources where appropriate;
L4 - relate mathematical and theoretical models of neural networks to their application in a science problem;
L5 - present results in written form to a mixed audience of experts in ML and of general scientists;
L6 - communicate results using appropriate styles, conventions and terminology.