Machine Learning - AIMS CDT - MT 2020, Week 4

AIMS CDT, 2 – 5 Nov 2020 (Microsoft Teams)
Lectures: 10:30 – 12:30, Practicals: 15:00 – 17:00

Machine learning is a collection of techniques that allow creation or tuning of models using example data or past experience. This course provides an introduction to machine learning with an emphasis on the recent research and application landscape. The course covers fundamental concepts including supervised and unsupervised learning, generative and discriminative modeling, differentiable programming, and a taxonomy of model architectures that are frequently used in practice. The course also covers probabilistic programming and simulation-based inference, including techniques at the intersection of probabilistic modeling and deep learning such as flow models.

This module is a part of the Autonomous Intelligent Machines and Systems (AIMS) Centre for Doctoral Training (CDT) programme.



Lecture slides will be linked from here before the beginning of each lecture.

Practicals and Assessment

The demonstrators for the practicals are Benjamin Moseley and Lewis Smith. The repository for the practicals and the assessed assignment can be found here.

Assignment deadline: 23:59 UK time, 9 Nov 2020


Basic linear algebra, calculus, probability theory, and programming (ideally in Python)

Reading material


Extra reading material