Sparse coupling and Markov blankets: A comment on "How particular is the physics of the Free Energy Principle?" by Aguilera, Millidge, Tschantz and Buckley.

@article{Heins2022SparseCA,
  title={Sparse coupling and Markov blankets: A comment on "How particular is the physics of the Free Energy Principle?" by Aguilera, Millidge, Tschantz and Buckley.},
  author={Conor Heins and Lancelot Da Costa},
  journal={Physics of life reviews},
  year={2022},
  volume={42},
  pages={
          33-39
        }
}

On Bayesian Mechanics: A Physics of and by Beliefs

A duality between the free energy principle and the constrained maximum entropy principle are examined, both of which lie at the heart of Bayesian mechanics.

Weak Markov Blankets in High-Dimensional, Sparsely-Coupled Random Dynamical Systems

. In this paper we formulate a notion of high-dimensional random dynamical systems that couple to another system, like an embedding environment, in such a way that each system engages in controlled

A Worked Example of the Bayesian Mechanics of Classical Objects

. Bayesian mechanics is a new approach to studying the mathematics and physics of interacting stochastic processes. In this note, we provide a worked example of a physical mechanics for classical

References

SHOWING 1-10 OF 16 REFERENCES

How particular is the physics of the free energy principle?

Stochastic Chaos and Markov Blankets

This treatment of random dynamical systems considers the existence—and identification— of conditional independencies at nonequilibrium steady-state, and shows how Markov blankets can be identified to characterise the coupling between internal and external states in terms of a generalised synchrony or synchronisation of chaos.

A free energy principle for a particular physics

The main contribution is to examine the implications of Markov blankets for self-organisation to nonequilibrium steady-state and recover an information geometry and accompanying free energy principle that allows one to interpret the internal states of something as representing or making inferences about its external states.

The free energy principle made simpler but not too simple

This paper provides a concise description of the free energy principle, starting from a formulation of random dynamical systems in terms of a Langevin equation and ending with a Bayesian mechanics

A Technical Critique of Some Parts of the Free Energy Principle

It is proved by counterexamples that the original free energy lemma, when taken at face value, is wrong and it is concluded that the interpretation in terms of Bayesian inference hinges on this point, and is not sufficiently justified.

Life as we know it

A heuristic proof suggesting that life—or biological self-organization—is an inevitable and emergent property of any (ergodic) random dynamical system that possesses a Markov blanket is presented.

Hydrodynamics and fluctuations outside of local equilibrium: Driven diffusive systems

We derive hydrodynamic equations for systems not in local thermodynamic equilibrium, that is, where the local stationary measures are “non-Gibbsian” and do not satisfy detailed balance with respect

Some Interesting Observations on the Free Energy Principle

This discussion focuses on solenoidal coupling between various states in sparsely coupled systems that possess a Markov blanket - and the distinction between exact and approximate Bayesian inference, implied by the ensuing Bayesian mechanics.

Bayesian mechanics for stationary processes

It follows that active states can be seen as performing active inference and well-known forms of stochastic control, which are prominent formulations of adaptive behaviour in theoretical biology and engineering.

A Unifying and Canonical Description of Measure-Preserving Diffusions

A complete recipe of measure-preserving diffusions in Euclidean space was recently derived unifying several MCMC algorithms into a single framework. In this paper, we develop a geometric theory that