- Academic Registry
Course & Unit Catalogues


MA50263: Mathematics of machine learning

[Page last updated: 09 August 2024]

Academic Year: 2024/25
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:
Semester 2
Assessment Summary: CWRI 100%
Assessment Detail:
  • Coursework (CWRI 100%)
Supplementary Assessment:
Like-for-like reassessment (where allowed by programme regulations)
Requisites: Before taking this module you must take MA50290
Learning Outcomes: After taking this unit, students should be able to:
* Formulate loss functions and test data and basic training algorithms.
* Write code to implement deep learning algorithms.
* Understand the importance of algorithm efficiency.
* Understand deep neural networks and their use in machine learning.


Synopsis: Develop a deeper understanding of modern machine learning, focusing on the underlying mathematics and numerical realisation of neural networks. By the end of the unit, you should be able to critically analyse the mathematical formulation of deep learning algorithms, implement them computationally and appreciate the importance of algorithm efficiency.

Aims: To develop students' knowledge and understanding of machine learning by introducing them to deep neural networks and their applications.

Skills: Formulation of machine learning problems TF, applications of neural networks TF, writing code for machine learning TFA, multi-dimensional calculus and optimization TA

Content: Deep learning algorithms and supporting techniques and mathematics including: Shallow v deep neural networks. Activation functions. Feed-forward networks. Convolutional networks. Recurrent networks. Backpropagation, initialisation, dropout, batch normalisation. Universal approximation of neural networks.

Course availability:

MA50263 is Compulsory on the following courses:

Department of Mathematical Sciences

MA50263 is Optional on the following courses:

Department of Mathematical Sciences
  • TSMA-AFM19 : MSc Mathematics with Data Science for Industry
  • TSMA-AWM19 : MSc Mathematics with Data Science for Industry

Notes:

  • This unit catalogue is applicable for the 2024/25 academic year only. Students continuing their studies into 2025/26 and beyond should not assume that this unit will be available in future years in the format displayed here for 2024/25.
  • Courses and units are subject to change in accordance with normal University procedures.
  • Availability of units will be subject to constraints such as staff availability, minimum and maximum group sizes, and timetabling factors as well as a student's ability to meet any pre-requisite rules.
  • Find out more about these and other important University terms and conditions here.