Bayesian mechanics for stationary processes

Cite This

Files in this item

Checksum: MD5:713091a00fa3bcbc6cd952ee383392f8

DA COSTA, Lancelot, Karl FRISTON, Conor HEINS, Grigorios A. PAVLIOTIS, 2021. Bayesian mechanics for stationary processes. In: Proceedings of the Royal Society of London, Series A : Mathematical, Physical and Engineering Sciences. Royal Society of London. 477(2256), 20210518. ISSN 1364-5021. eISSN 1471-2946. Available under: doi: 10.1098/rspa.2021.0518

@article{DaCosta2021Bayes-55927, title={Bayesian mechanics for stationary processes}, year={2021}, doi={10.1098/rspa.2021.0518}, number={2256}, volume={477}, issn={1364-5021}, journal={Proceedings of the Royal Society of London, Series A : Mathematical, Physical and Engineering Sciences}, author={Da Costa, Lancelot and Friston, Karl and Heins, Conor and Pavliotis, Grigorios A.}, note={Article Number: 20210518} }

<rdf:RDF xmlns:dcterms="" xmlns:dc="" xmlns:rdf="" xmlns:bibo="" xmlns:dspace="" xmlns:foaf="" xmlns:void="" xmlns:xsd="" > <rdf:Description rdf:about=""> <dcterms:issued>2021</dcterms:issued> <dcterms:abstract xml:lang="eng">This paper develops a Bayesian mechanics for adaptive systems. Firstly, we model the interface between a system and its environment with a Markov blanket. This affords conditions under which states internal to the blanket encode information about external states. Second, we introduce dynamics and represent adaptive systems as Markov blankets at steady state. This allows us to identify a wide class of systems whose internal states appear to infer external states, consistent with variational inference in Bayesian statistics and theoretical neuroscience. Finally, we partition the blanket into sensory and active states. It follows that active states can be seen as performing active inference and well-known forms of stochastic control (such as PID control), which are prominent formulations of adaptive behaviour in theoretical biology and engineering.</dcterms:abstract> <dc:creator>Da Costa, Lancelot</dc:creator> <dc:contributor>Friston, Karl</dc:contributor> <dc:creator>Friston, Karl</dc:creator> <dcterms:isPartOf rdf:resource=""/> <dspace:isPartOfCollection rdf:resource=""/> <dcterms:isPartOf rdf:resource=""/> <dcterms:rights rdf:resource=""/> <dspace:hasBitstream rdf:resource=""/> <bibo:uri rdf:resource=""/> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <dcterms:hasPart rdf:resource=""/> <dc:creator>Pavliotis, Grigorios A.</dc:creator> <dc:date rdf:datatype="">2021-12-20T08:41:06Z</dc:date> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dspace:isPartOfCollection rdf:resource=""/> <dc:contributor>Heins, Conor</dc:contributor> <dc:contributor>Pavliotis, Grigorios A.</dc:contributor> <dc:creator>Heins, Conor</dc:creator> <dc:language>eng</dc:language> <dc:rights>terms-of-use</dc:rights> <dcterms:title>Bayesian mechanics for stationary processes</dcterms:title> <dc:contributor>Da Costa, Lancelot</dc:contributor> <dcterms:available rdf:datatype="">2021-12-20T08:41:06Z</dcterms:available> </rdf:Description> </rdf:RDF>

Downloads since Dec 20, 2021 (Information about access statistics)

DaCosta_2-71cm7stsluyo6.pdf 64

This item appears in the following Collection(s)

Search KOPS


My Account