Markov Blanket Density and Free Energy Minimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Possati, Luca M.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912529434804224
author Possati, Luca M.
author_facet Possati, Luca M.
contents This paper presents a continuous, information-theoretic extension of the Free Energy Principle through the concept of Markov blanket density, i.e., a scalar field that quantifies the degree of conditional independence between internal and external states at each point in space (ranging from 0 for full coupling to 1 for full separation). It demonstrates that active inference dynamics, including the minimization of variational and expected free energy, naturally emerge from spatial gradients in this density, making Markov blanket density a necessary foundation for the Free Energy Principle. These ideas are developed through a mathematically framework that links density gradients to precise and testable dynamics, offering a foundation for novel predictions and simulation paradigms.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05794
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Markov Blanket Density and Free Energy Minimization
Possati, Luca M.
Neurons and Cognition
Information Theory
This paper presents a continuous, information-theoretic extension of the Free Energy Principle through the concept of Markov blanket density, i.e., a scalar field that quantifies the degree of conditional independence between internal and external states at each point in space (ranging from 0 for full coupling to 1 for full separation). It demonstrates that active inference dynamics, including the minimization of variational and expected free energy, naturally emerge from spatial gradients in this density, making Markov blanket density a necessary foundation for the Free Energy Principle. These ideas are developed through a mathematically framework that links density gradients to precise and testable dynamics, offering a foundation for novel predictions and simulation paradigms.
title Markov Blanket Density and Free Energy Minimization
topic Neurons and Cognition
Information Theory
url https://arxiv.org/abs/2506.05794