Back to research

Machine learning theory and methods

Overview

Probability provides a language for us to describe our knowledge (or ignorance) of the world. To building statistical models, we need to structure our knowledge about a specific system such that we can reduce our ignorance using observations. These techniques are essential components for building interpretable computational structures that can be used for decision making.

Projects

Information Topography

Information topography is the geometry of how information flows through a complex system. The programme develops the mathematical foundations of that geometry — from information-theoretic axioms to predictive accounts of how communication structure emerges and reorganises.