N/A

This module aims to extend the Fundaments of machine learning module. In particular, students will gain a deeper knowledge of modem machine learning algorithms, with an emphasis of neural networks for image analysis tasks (e.g., classification, regression, segmentation). The syllabus of this module includes:
Probability theory: introduction, discrete and continuous probability function, Bayesian classifier,
information theory.
- Image analysis: colour spaces,com.olution, edge detection, image representation, image descriptors
- Neural netoorks: multi-layer perceptron, com.olutional layers, initialisation, optimisers
In the last part of the module, the students will learn about state-of-the-art deep neural network
architectures, putting them in the context of classification and regression tasks.

LO1: Critically evaluate the use of machine learning algorithms
L02: Develop new skills in image analysis using deep networks
LO3: Critically evaluate the different layers in a deep network
L04: Critically evaluate the different action functions and optimisers
LOS: Design, develop, and evaluate customised deep networks applications in Python
L06: Critically report the results in a scientific form and draw appropriate conclusions.