Publikation: Federated inference and belief sharing
Dateien
Datum
Autor:innen
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
URI (zitierfähiger Link)
DOI (zitierfähiger Link)
Internationale Patentnummer
Link zur Lizenz
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Publikationsstatus
Erschienen in
Zusammenfassung
This paper concerns the distributed intelligence or federated inference that emerges under belief-sharing among agents who share a common world—and world model. Imagine, for example, several animals keeping a lookout for predators. Their collective surveillance rests upon being able to communicate their beliefs—about what they see—among themselves. But, how is this possible? Here, we show how all the necessary components arise from minimising free energy. We use numerical studies to simulate the generation, acquisition and emergence of language in synthetic agents. Specifically, we consider inference, learning and selection as minimising the variational free energy of posterior (i.e., Bayesian) beliefs about the states, parameters and structure of generative models, respectively. The common theme—that attends these optimisation processes—is the selection of actions that minimise expected free energy, leading to active inference, learning and model selection (a.k.a., structure learning). We first illustrate the role of communication in resolving uncertainty about the latent states of a partially observed world, on which agents have complementary perspectives. We then consider the acquisition of the requisite language—entailed by a likelihood mapping from an agent’s beliefs to their overt expression (e.g., speech)—showing that language can be transmitted across generations by active learning. Finally, we show that language is an emergent property of free energy minimisation, when agents operate within the same econiche. We conclude with a discussion of various perspectives on these phenomena; ranging from cultural niche construction, through federated learning, to the emergence of complexity in ensembles of selforganising systems.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
Schlagwörter
Konferenz
Rezension
Zitieren
ISO 690
FRISTON, Karl J., Thomas PARR, Conor HEINS, Axel CONSTANT, Daniel FRIEDMAN, Takuya ISOMURA, Chris FIELDS, Tim VERBELEN, Maxwell RAMSTEAD, John CLIPPINGER, 2024. Federated inference and belief sharing. In: Neuroscience and Biobehavioral Reviews. Elsevier. 2024, 156, pp. 105500-105500. ISSN 0149-7634. Available under: doi: 10.1016/j.neubiorev.2023.105500BibTex
@article{Friston2024-01Feder-69145, year={2024}, doi={10.1016/j.neubiorev.2023.105500}, title={Federated inference and belief sharing}, volume={156}, issn={0149-7634}, journal={Neuroscience and Biobehavioral Reviews}, pages={105500--105500}, author={Friston, Karl J. and Parr, Thomas and Heins, Conor and Constant, Axel and Friedman, Daniel and Isomura, Takuya and Fields, Chris and Verbelen, Tim and Ramstead, Maxwell and Clippinger, John}, note={Article Number: 105500} }
RDF
<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:bibo="http://purl.org/ontology/bibo/" xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:void="http://rdfs.org/ns/void#" xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/69145"> <dc:contributor>Friston, Karl J.</dc:contributor> <dc:contributor>Constant, Axel</dc:contributor> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/43615"/> <dc:creator>Friedman, Daniel</dc:creator> <dc:creator>Isomura, Takuya</dc:creator> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/28"/> <dc:contributor>Clippinger, John</dc:contributor> <dc:contributor>Parr, Thomas</dc:contributor> <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/69145/1/Friston_2-1434gs3n9ngp26.pdf"/> <dc:language>eng</dc:language> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-01-22T10:23:40Z</dc:date> <dc:creator>Heins, Conor</dc:creator> <dc:creator>Friston, Karl J.</dc:creator> <dcterms:title>Federated inference and belief sharing</dcterms:title> <dc:contributor>Friedman, Daniel</dc:contributor> <dcterms:issued>2024-01</dcterms:issued> <dc:rights>Attribution 4.0 International</dc:rights> <dc:creator>Fields, Chris</dc:creator> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/69145"/> <dc:creator>Ramstead, Maxwell</dc:creator> <dcterms:abstract>This paper concerns the distributed intelligence or federated inference that emerges under belief-sharing among agents who share a common world—and world model. Imagine, for example, several animals keeping a lookout for predators. Their collective surveillance rests upon being able to communicate their beliefs—about what they see—among themselves. But, how is this possible? Here, we show how all the necessary components arise from minimising free energy. We use numerical studies to simulate the generation, acquisition and emergence of language in synthetic agents. Specifically, we consider inference, learning and selection as minimising the variational free energy of posterior (i.e., Bayesian) beliefs about the states, parameters and structure of generative models, respectively. The common theme—that attends these optimisation processes—is the selection of actions that minimise expected free energy, leading to active inference, learning and model selection (a.k.a., structure learning). We first illustrate the role of communication in resolving uncertainty about the latent states of a partially observed world, on which agents have complementary perspectives. We then consider the acquisition of the requisite language—entailed by a likelihood mapping from an agent’s beliefs to their overt expression (e.g., speech)—showing that language can be transmitted across generations by active learning. Finally, we show that language is an emergent property of free energy minimisation, when agents operate within the same econiche. We conclude with a discussion of various perspectives on these phenomena; ranging from cultural niche construction, through federated learning, to the emergence of complexity in ensembles of selforganising systems.</dcterms:abstract> <dc:creator>Parr, Thomas</dc:creator> <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/69145/1/Friston_2-1434gs3n9ngp26.pdf"/> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-01-22T10:23:40Z</dcterms:available> <dc:creator>Constant, Axel</dc:creator> <dc:contributor>Heins, Conor</dc:contributor> <dc:contributor>Isomura, Takuya</dc:contributor> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dc:creator>Verbelen, Tim</dc:creator> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/43615"/> <dc:creator>Clippinger, John</dc:creator> <dc:contributor>Ramstead, Maxwell</dc:contributor> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/28"/> <foaf:homepage rdf:resource="http://localhost:8080/"/> <dcterms:rights rdf:resource="http://creativecommons.org/licenses/by/4.0/"/> <dc:contributor>Fields, Chris</dc:contributor> <dc:contributor>Verbelen, Tim</dc:contributor> </rdf:Description> </rdf:RDF>