Cargando…

Canonical neural networks perform active inference

This work considers a class of canonical neural networks comprising rate coding models, wherein neural activity and plasticity minimise a common cost function—and plasticity is modulated with a certain delay. We show that such neural networks implicitly perform active inference and learning to minim...

Descripción completa

Detalles Bibliográficos
Autores principales: Isomura, Takuya, Shimazaki, Hideaki, Friston, Karl J.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8760273/
https://www.ncbi.nlm.nih.gov/pubmed/35031656
http://dx.doi.org/10.1038/s42003-021-02994-2
_version_ 1784633282528280576
author Isomura, Takuya
Shimazaki, Hideaki
Friston, Karl J.
author_facet Isomura, Takuya
Shimazaki, Hideaki
Friston, Karl J.
author_sort Isomura, Takuya
collection PubMed
description This work considers a class of canonical neural networks comprising rate coding models, wherein neural activity and plasticity minimise a common cost function—and plasticity is modulated with a certain delay. We show that such neural networks implicitly perform active inference and learning to minimise the risk associated with future outcomes. Mathematical analyses demonstrate that this biological optimisation can be cast as maximisation of model evidence, or equivalently minimisation of variational free energy, under the well-known form of a partially observed Markov decision process model. This equivalence indicates that the delayed modulation of Hebbian plasticity—accompanied with adaptation of firing thresholds—is a sufficient neuronal substrate to attain Bayes optimal inference and control. We corroborated this proposition using numerical analyses of maze tasks. This theory offers a universal characterisation of canonical neural networks in terms of Bayesian belief updating and provides insight into the neuronal mechanisms underlying planning and adaptive behavioural control.
format Online
Article
Text
id pubmed-8760273
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-87602732022-01-26 Canonical neural networks perform active inference Isomura, Takuya Shimazaki, Hideaki Friston, Karl J. Commun Biol Article This work considers a class of canonical neural networks comprising rate coding models, wherein neural activity and plasticity minimise a common cost function—and plasticity is modulated with a certain delay. We show that such neural networks implicitly perform active inference and learning to minimise the risk associated with future outcomes. Mathematical analyses demonstrate that this biological optimisation can be cast as maximisation of model evidence, or equivalently minimisation of variational free energy, under the well-known form of a partially observed Markov decision process model. This equivalence indicates that the delayed modulation of Hebbian plasticity—accompanied with adaptation of firing thresholds—is a sufficient neuronal substrate to attain Bayes optimal inference and control. We corroborated this proposition using numerical analyses of maze tasks. This theory offers a universal characterisation of canonical neural networks in terms of Bayesian belief updating and provides insight into the neuronal mechanisms underlying planning and adaptive behavioural control. Nature Publishing Group UK 2022-01-14 /pmc/articles/PMC8760273/ /pubmed/35031656 http://dx.doi.org/10.1038/s42003-021-02994-2 Text en © The Author(s) 2022 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Article
Isomura, Takuya
Shimazaki, Hideaki
Friston, Karl J.
Canonical neural networks perform active inference
title Canonical neural networks perform active inference
title_full Canonical neural networks perform active inference
title_fullStr Canonical neural networks perform active inference
title_full_unstemmed Canonical neural networks perform active inference
title_short Canonical neural networks perform active inference
title_sort canonical neural networks perform active inference
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8760273/
https://www.ncbi.nlm.nih.gov/pubmed/35031656
http://dx.doi.org/10.1038/s42003-021-02994-2
work_keys_str_mv AT isomuratakuya canonicalneuralnetworksperformactiveinference
AT shimazakihideaki canonicalneuralnetworksperformactiveinference
AT fristonkarlj canonicalneuralnetworksperformactiveinference