eprintid: 10160279
rev_number: 7
eprint_status: archive
userid: 699
dir: disk0/10/16/02/79
datestamp: 2022-11-24 17:14:12
lastmod: 2022-11-24 17:14:12
status_changed: 2022-11-24 17:14:12
type: article
metadata_visibility: show
sword_depositor: 699
creators_name: Neacsu, Victorita
creators_name: Mirza, M Berk
creators_name: Adams, Rick A
creators_name: Friston, Karl J
title: Structure learning enhances concept formation in synthetic Active Inference agents
ispublished: pub
divisions: UCL
divisions: B02
divisions: C07
divisions: D79
divisions: D07
divisions: F83
divisions: FH4
keywords: Learning, Free energy, Foraging, Sensory perception, Probability distribution, Agent-based modeling, Machine learning, Behavior
note: Copyright © 2022 Neacsu et al. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
abstract: Humans display astonishing skill in learning about the environment in which they operate. They assimilate a rich set of affordances and interrelations among different elements in particular contexts, and form flexible abstractions (i.e., concepts) that can be generalised and leveraged with ease. To capture these abilities, we present a deep hierarchical Active Inference model of goal-directed behaviour, and the accompanying belief update schemes implied by maximising model evidence. Using simulations, we elucidate the potential mechanisms that underlie and influence concept learning in a spatial foraging task. We show that the representations formed-as a result of foraging-reflect environmental structure in a way that is enhanced and nuanced by Bayesian model reduction, a special case of structure learning that typifies learning in the absence of new evidence. Synthetic agents learn associations and form concepts about environmental context and configuration as a result of inferential, parametric learning, and structure learning processes-three processes that can produce a diversity of beliefs and belief structures. Furthermore, the ensuing representations reflect symmetries for environments with identical configurations.
date: 2022-11-14
date_type: published
publisher: Public Library of Science (PLoS)
official_url: https://doi.org/10.1371/journal.pone.0277199
oa_status: green
full_text_type: pub
language: eng
primo: open
primo_central: open_green
verified: verified_manual
elements_id: 1990340
doi: 10.1371/journal.pone.0277199
medium: Electronic-eCollection
pii: PONE-D-21-27876
lyricists_name: Friston, Karl
lyricists_name: Adams, Richard
lyricists_id: KJFRI52
lyricists_id: RAADA06
actors_name: Flynn, Bernadette
actors_id: BFFLY94
actors_role: owner
funding_acknowledgements: MR/S007806/1 [Medical Research Council]; 088130/Z/09/Z [Wellcome Trust]
full_text_status: public
publication: PLOS ONE
volume: 17
number: 11
article_number: e0277199
event_location: United States
issn: 1932-6203
citation:        Neacsu, Victorita;    Mirza, M Berk;    Adams, Rick A;    Friston, Karl J;      (2022)    Structure learning enhances concept formation in synthetic Active Inference agents.                   PLOS ONE , 17  (11)    , Article e0277199.  10.1371/journal.pone.0277199 <https://doi.org/10.1371/journal.pone.0277199>.       Green open access   
 
document_url: https://discovery.ucl.ac.uk/id/eprint/10160279/1/journal.pone.0277199.pdf