The free energy principle made simpler but not too simple

Abstract

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 that can be read as a physics of sentience. It rehearses the key steps using standard results from statistical physics. These steps entail (i) establishing a particular partition of states based upon conditional independencies that inherit from sparsely coupled dynamics, (ii) unpacking the implications of this partition in terms of Bayesian inference and (iii) describing the paths of particular states with a variational principle of least action. Teleologically, the free energy principle offers a normative account of self-organisation in terms of optimal Bayesian design and decision-making, in the sense of maximising marginal likelihood or Bayesian model evidence. In summary, starting from a description of the world in terms of random dynamical systems, we end up with a description of self-organisation as sentient behaviour that can be interpreted as self-evidencing; namely, self-assembly, autopoiesis or active inference.

arXiv comment44 pages, 9 Figures; 64 pages including graphical abstract, highlights and references

References in corpus (26)

• A nonequilibrium equality for free energy differences
• Stochastic thermodynamics, fluctuation theorems, and molecular machines
• The information bottleneck method
• Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review
• Path integrals and symmetry breaking for optimal control theory
• Optimal control as a graphical model inference problem
• The thermodynamics of prediction
• Stochastic Dynamical Structure (SDS) of Nonequilibrium Processes in the Absence of Detailed Balance. II: construction of SDS with nonlinear force and multiplicative noise
• A free energy principle for a particular physics
• Active inference on discrete state-spaces: a synthesis
• A Complete Recipe for Stochastic Gradient MCMC
• Active inference: demystified and compared
• Optimal non-reversible linear drift for the convergence to equilibrium of a diffusion
• Path integrals, particular kinds, and strange things
• Accelerating diffusions
• Deep Active Inference
• Modeling somatic computation with non-neural bioelectric networks
• Relation of a New Interpretation of Stochastic Differential Equations to Ito Process
• Neural dynamics under active inference: plausibility and efficiency of information processing
• A Gauge Theoretic Approach to Gravity
• The broad edge of synchronisation: Griffiths effects and collective phenomena in brain networks
• Bayesian Mechanics for Stationary Processes
• A path integral formalism for non-equilibrium Hamiltonian statistical systems
• Optimal design of experiments to identify latent behavioral types
• Perturbative Expansion of Irreversible Work in Fokker-Planck Equation a la Quantum Mechanics
• Entropy-Maximising Diffusions Satisfy a Parallel Transport Law

Cited by in corpus (15)

• On Bayesian Mechanics: A Physics of and by Beliefs
• Collective behavior from surprise minimization
• Equilibrium in the Computing Continuum through Active Inference
• Intelligent Soft Matter: Towards Embodied Intelligence
• Quantum formalism for cognitive psychology
• On efficient computation in active inference
• Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents
• A Worked Example of the Bayesian Mechanics of Classical Objects
• Self-orthogonalizing attractor neural networks emerging from the free energy principle
• Regarding Flows Under the Free Energy Principle: A Comment on "How Particular is the Physics of the Free Energy Principle?" by Aguilera, Millidge, Tschantz, and Buckley
• Why collective behaviours self-organise to criticality: A primer on information-theoretic and thermodynamic utility measures
• A unified framework for divergences, free energies, and Fokker-Planck equations
• Universal scaling limits for spin networks via martingale methods
• Particular flows and attracting sets: A comment on "How particular is the physics of the Free Energy Principle?" by Aguilera, Millidge, Tschantz and Buckley
• Generalized Inverse Optimal Control and its Application in Biology