Machine Learning in Science Part I
| Code | School | Level | Credits | Semesters |
| PHYS4035 | Physics and Astronomy | 4 | 20 | Autumn UK |
- Code
- PHYS4035
- School
- Physics and Astronomy
- Level
- 4
- Credits
- 20
- Semesters
- Autumn UK
Summary
This module will provide an introduction to the main concepts and methods of machine learning. It is the first of the core modules of the MLiS MSc. It will be taught via weekly lectures and/or workshops, comprising topical discussions on fundamental aspects of ML, and the solving of concrete examples problems.
Target Students
Only available to students doing the Machine Learning in Science MSc and the Computational Neuroscience, Cognition & AI MSc.
Assessment
- 40% PRESENTATION: Group presentation on selected topic.
- 60% REPORT: Account of mini-project in the form of a PRL-style paper
Assessed by end of autumn semester
Educational Aims
The purpose of this module is to provide an introduction to the concepts and methods of modern machine learning. It will cover the basics of supervised learning, unsupervised and reinforcement learning, as applied to a variety of problems of linear and non-linear regression, classification, density estimation and data generation and optimal control. It will be a combination of fundamental concepts and hands on application to a selection of example problems.Learning Outcomes
A student who completes this course successfully should:
L1 - be familiar with the main concepts of machine learning, including supervised and, unsupervised and reinforcement learning.
L2 - be able to solve simple problems of regression, classification, density estimation and data generation via elementary machine learning techniques;
L3 - Be familiar with basic ideas of artificial neural networks and how to apply them for ML purposes.