On Bayesian mechanics: a physics of and by beliefs

Abstract

The aim of this paper is to introduce a field of study that has emerged over the last decade, called Bayesian mechanics. Bayesian mechanics is a probabilistic mechanics, comprising tools that enable us to model systems endowed with a particular partition (i.e. into particles), where the internal states (or the trajectories of internal states) of a particular system encode the parameters of beliefs about external states (or their trajectories). These tools allow us to write down mechanical theories for systems that look as if they are estimating posterior probability distributions over the causes of their sensory states. This provides a formal language for modelling the constraints, forces, potentials and other quantities determining the dynamics of such systems, especially as they entail dynamics on a space of beliefs (i.e. on a statistical manifold). Here, we will review the state of the art in the literature on the free energy principle, distinguishing between three ways in which Bayesian mechanics has been applied to particular systems (i.e. path-tracking, mode-tracking and mode-matching). We go on to examine a duality between the free energy principle and the constrained maximum entropy principle, both of which lie at the heart of Bayesian mechanics, and discuss its implications.

Document Details

Document Type
Pub Defense Publication
Publication Date
Apr 14, 2023
Source ID
10.1098/rsfs.2022.0029

Entities

People

  • Beren Millidge
  • Brennan Klein
  • Conor Heins
  • Dalton A R Sakthivadivel
  • Karl J. Friston
  • Lancelot Da Costa
  • Magnus Koudahl
  • Maxwell J. D. Ramstead

Organizations

  • Biotechnology and Biological Sciences Research Council
  • Eindhoven University of Technology
  • Imperial College London
  • John Templeton Foundation
  • Max Planck Institute of Animal Behavior
  • Medical Research Council
  • National Research Fund Luxembourg
  • Northeastern University
  • Office of Naval Research
  • Stony Brook University
  • University College London
  • University of Konstanz
  • University of Oxford
  • Wellcome

Tags

Readers

  • Artificial Intelligence
  • Robotics and Automation.
  • Theoretical Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • Space