Markov blankets, information geometry and stochastic thermodynamics. (23rd December 2019)

• Record Type: Journal Article
• Authors: Parr, Thomas; Da Costa, Lancelot; Friston, Karl
• Is Part Of: Philosophical transactions. Volume 378:Number 2164(2020)
• Publication Date: 2019-12-23
• Subjects: thermodynamics -- information geometry -- variational inference -- Bayesian -- Markov blanket; Physical sciences -- Periodicals; Engineering -- Periodicals; Mathematics -- Periodicals; 500
• DOI: 10.1098/rsta.2019.0159
• Languages: English
• ISSNs: 1364-503X

Abstract

Abstract : This paper considers the relationship between thermodynamics, information and inference. In particular, it explores the thermodynamic concomitants of belief updating, under a variational (free energy) principle for self-organization. In brief, any (weakly mixing) random dynamical system that possesses a Markov blanket—i.e. a separation of internal and external states—is equipped with an information geometry. This means that internal states parametrize a probability density over external states. Furthermore, at non-equilibrium steady-state, the flow of internal states can be construed as a gradient flow on a quantity known in statistics as Bayesian model evidence. In short, there is a natural Bayesian mechanics for any system that possesses a Markov blanket. Crucially, this means that there is an explicit link between the inference performed by internal states and their energetics—as characterized by their stochastic thermodynamics. This article is part of the theme issue 'Harmonizing energy-autonomous computing and intelligence'.