Machine Learning in Science Part II
| Code | School | Level | Credits | Semesters |
| PHYS4036 | Physics and Astronomy | 4 | 20 | Spring UK |
- Code
- PHYS4036
- School
- Physics and Astronomy
- Level
- 4
- Credits
- 20
- Semesters
- Spring UK
Summary
This module will cover more advanced topics of machine learning and neural networks following from PHYS4035 (Machine Learning in Science Part I). It is the second of the core modules of the MLiS MSc. It will be taught via two classes per week, comprising topical discussions, concrete examples of ML in science and lectures on the statistical foundations of ML.
Target Students
PGT Students on the MSc Machine Learning in Science Programme OR the MSc Neuroscience Programmes
Co-requisites
Modules you must take in the same academic year, or have taken in a previous year, to enrol in this module:
Classes
Mini- project activity
Assessment
- 40% PRESENTATION: 30 minute individual presentation
- 60% REPORT: Account of mini-project in the form of a PRL-style paper
Assessed by end of spring semester
Educational Aims
The purpose of this module is to cover more advanced topics in ML and artificial neural networks following PHYS4035 (Machine Learning in Science Part I). Topics to be covered will include deep neural networks and deep supervised learning; convolutional NNs, RNNs, GANs; unsupervised learning, restricted Boltzmann machines, deep RBMs and autoencoders; reinforcement learning and Markov decision processes; cleaning data and handling large data sets. Concepts will be applied to associated small projects.Learning Outcomes
A student who completes this course successfully should:
L1 - be familiar with the advanced concepts of machine learning, including supervised, unsupervised and reinforcement learning;
L2 - be able to solve advanced problems of classification, generation, data compression, and optimisation;
L3 - be familiar with ideas of artificial deep neural networks and how to apply them to specific targeted projects.