MA50263: Mathematics of machine learning
[Page last updated: 23 October 2023]
Academic Year:  2023/24 
Owning Department/School:  Department of Mathematical Sciences 
Credits:  6 [equivalent to 12 CATS credits] 
Notional Study Hours:  120 
Level:  Masters UG & PG (FHEQ level 7) 
Period: 

Assessment Summary:  CW 100% 
Assessment Detail: 

Supplementary Assessment: 

Requisites: 
Must have Programming ability in Python or other highlevel language. Graduate level mathematics skills.
In taking this module you cannot take CM50265 
Learning Outcomes: 
After taking this unit, students should be able to:
* Demonstrate knowledge of modern machine learning techniques * Use computational tools for applying machine learning * Show awareness of the applications of these methods * Understand the mathematical models underlying machine learning algorithms and details of their implementation * Write the relevant mathematical arguments in a precise and lucid fashion. 
Aims:  To teach Machine Learning, including theoretical background and tools for implementation, to statistical applied mathematicians. 
Skills:  Problem Solving (T,F&A), Computing (T,F&A), independent study and report writing. 
Content:  Introduction to machine learning (supervised vs unsupervised learning, generative vs discriminative models, validation, regression vs neural networks, computational tools in Python).
Additional topics will be chosen from: * Neural networks (feedforward, convolution, recurrent networks). Universal approximation theorem. Gradient descent * Graphical models (decision trees, random forests, Markov random fields, Boltzmann machines) * Bayesian nonparametric (Gaussian and Dirichlet process regression, hyper parameters) * Reinforcement learning * Shrinkage methods. 
Course availability: 
MA50263 is Optional on the following courses:Department of Mathematical Sciences

Notes:
