Description
This module will introduce the student to the theoretical foundations behind some of the most widespread methods used in Machine Learning and Artificial Intelligence. We will dive deeply into the mathematical foundations of three learning paradigms, embodied in one flagship method within each one: (i) Linear regression for supervised learning, (ii) principal component analysis for unsupervised learning, and (iii) backpropagation for deep learning. Additionally, we will study the mathematics behind diffusion models, currently one of the most notable generative AI methods to produce images from text. Besides the theoretical aspects of these techniques, students will be exposed to practical implementation of machine learning algorithms through practical examples shown during lectures. Online tutorials on the coding (in Python) of the studied methods will be provided.
Module deliveries for 2024/25 academic year
Last updated
This module description was last updated on 19th August 2024.
Ìý