Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387355924> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4387355924 abstract "Compositionality is an important feature of discrete symbolic systems, such as language and programs, as it enables them to have infinite capacity despite a finite symbol set. It serves as a useful abstraction for reasoning in both cognitive science and in AI, yet the interface between continuous and symbolic processing is often imposed by fiat at the algorithmic level, such as by means of quantization or a softmax sampling step. In this work, we explore how discretization could be implemented in a more neurally plausible manner through the modeling of attractor dynamics that partition the continuous representation space into basins that correspond to sequences of symbols. Building on established work in attractor networks and introducing novel training methods, we show that imposing structure in the symbolic space can produce compositionality in the attractor-supported representation space of rich sensory inputs. Lastly, we argue that our model exhibits the process of an information bottleneck that is thought to play a role in conscious experience, decomposing the rich information of a sensory input into stable components encoding symbolic information." @default.
- W4387355924 created "2023-10-05" @default.
- W4387355924 creator A5019075836 @default.
- W4387355924 creator A5027171832 @default.
- W4387355924 creator A5043037494 @default.
- W4387355924 creator A5058010139 @default.
- W4387355924 creator A5068089852 @default.
- W4387355924 creator A5086198262 @default.
- W4387355924 date "2023-10-03" @default.
- W4387355924 modified "2023-10-06" @default.
- W4387355924 title "Discrete, compositional, and symbolic representations through attractor dynamics" @default.
- W4387355924 doi "https://doi.org/10.48550/arxiv.2310.01807" @default.
- W4387355924 hasPublicationYear "2023" @default.
- W4387355924 type Work @default.
- W4387355924 citedByCount "0" @default.
- W4387355924 crossrefType "posted-content" @default.
- W4387355924 hasAuthorship W4387355924A5019075836 @default.
- W4387355924 hasAuthorship W4387355924A5027171832 @default.
- W4387355924 hasAuthorship W4387355924A5043037494 @default.
- W4387355924 hasAuthorship W4387355924A5058010139 @default.
- W4387355924 hasAuthorship W4387355924A5068089852 @default.
- W4387355924 hasAuthorship W4387355924A5086198262 @default.
- W4387355924 hasBestOaLocation W43873559241 @default.
- W4387355924 hasConcept C121375916 @default.
- W4387355924 hasConcept C134306372 @default.
- W4387355924 hasConcept C154945302 @default.
- W4387355924 hasConcept C16101541 @default.
- W4387355924 hasConcept C164380108 @default.
- W4387355924 hasConcept C17744445 @default.
- W4387355924 hasConcept C199539241 @default.
- W4387355924 hasConcept C202444582 @default.
- W4387355924 hasConcept C2776359362 @default.
- W4387355924 hasConcept C33923547 @default.
- W4387355924 hasConcept C41008148 @default.
- W4387355924 hasConcept C80444323 @default.
- W4387355924 hasConcept C94625758 @default.
- W4387355924 hasConceptScore W4387355924C121375916 @default.
- W4387355924 hasConceptScore W4387355924C134306372 @default.
- W4387355924 hasConceptScore W4387355924C154945302 @default.
- W4387355924 hasConceptScore W4387355924C16101541 @default.
- W4387355924 hasConceptScore W4387355924C164380108 @default.
- W4387355924 hasConceptScore W4387355924C17744445 @default.
- W4387355924 hasConceptScore W4387355924C199539241 @default.
- W4387355924 hasConceptScore W4387355924C202444582 @default.
- W4387355924 hasConceptScore W4387355924C2776359362 @default.
- W4387355924 hasConceptScore W4387355924C33923547 @default.
- W4387355924 hasConceptScore W4387355924C41008148 @default.
- W4387355924 hasConceptScore W4387355924C80444323 @default.
- W4387355924 hasConceptScore W4387355924C94625758 @default.
- W4387355924 hasLocation W43873559241 @default.
- W4387355924 hasOpenAccess W4387355924 @default.
- W4387355924 hasPrimaryLocation W43873559241 @default.
- W4387355924 hasRelatedWork W1526190050 @default.
- W4387355924 hasRelatedWork W1973534662 @default.
- W4387355924 hasRelatedWork W2010490241 @default.
- W4387355924 hasRelatedWork W2100837828 @default.
- W4387355924 hasRelatedWork W2477397717 @default.
- W4387355924 hasRelatedWork W3095531775 @default.
- W4387355924 hasRelatedWork W3192500523 @default.
- W4387355924 hasRelatedWork W4251923961 @default.
- W4387355924 hasRelatedWork W4287025733 @default.
- W4387355924 hasRelatedWork W2500457737 @default.
- W4387355924 isParatext "false" @default.
- W4387355924 isRetracted "false" @default.
- W4387355924 workType "article" @default.