MA50290: Applied 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: | CWRI 100% |
Assessment Detail: |
|
Supplementary Assessment: |
|
Requisites: | You must have familiarity with linear algebra (vectors and matrices) and multivariable calculus (especially partial derivatives and the chain rule) to take this module. |
Learning Outcomes: |
After taking this module students will be able to:
|
Synopsis: | You will develop knowledge and understanding of Machine Learning using deep neural networks |
Aims: | This module will 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 in python
TFA, multi-dimensional calculus and optimization TA |
Content: | Machine Learning algorithms and supporting techniques and mathematics including some of the following:
1. Supervised learning and neural networks. 2. Preliminaries (linear algebra and multi-variable calculus, Python include machine-learning packages). 3. Logistic regression and gradient-descent training algorithms, with examples in Python. 4. Shallow neural networks (activation functions, training, initialisation). 5. Deep neural networks (motivation, training, forward backward propagation). 6. Applications and practical issues. |
Course availability: |
MA50290 is Compulsory on the following courses:Department of Mathematical Sciences
|
Notes:
|