Bayesian Mechanics for Stationary Processes

Grigorios A. Pavliotis, Karl Friston, Conor Heins, Lancelot Da Costa

Publication date: 25 June 2021

Abstract: This paper develops a Bayesian mechanics for adaptive systems. Firstly, we model the interface between a system and its environment with a Markov blanket. This affords conditions under which states internal to the blanket encode information about external states. Second, we introduce dynamics and represent adaptive systems as Markov blankets at steady-state. This allows us to identify a wide class of systems whose internal states appear to infer external states, consistent with variational inference in Bayesian statistics and theoretical neuroscience. Finally, we partition the blanket into sensory and active states. It follows that active states can be seen as performing active inference and well-known forms of stochastic control (such as PID control), which are prominent formulations of adaptive behaviour in theoretical biology and engineering.

Has companion code repository: https://github.com/conorheins/bayesian-mechanics-sdes

This page was built for publication: Bayesian Mechanics for Stationary Processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6371286)