Matches in SemOpenAlex for { <https://semopenalex.org/work/W2894810083> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2894810083 abstract "Humans learn complex latent structures from their environments (e.g., natural language, mathematics, music, social hierarchies). In cognitive science and cognitive neuroscience, models that infer higher-order structures from sensory or first-order representations have been proposed to account for the complexity and flexibility of human behavior. But how do the structures that these models invoke arise in neural systems in the first place? To answer this question, we explain how a system can learn latent representational structures (i.e., predicates) from experience with wholly unstructured data. During the process of predicate learning, an artificial neural network exploits the naturally occurring dynamic properties of distributed computing across neuronal assemblies in order to learn predicates, but also to combine them compositionally, two computational aspects which appear to be necessary for human behavior as per formal theories in multiple domains. We describe how predicates can be combined generatively using neural oscillations to achieve human-like extrapolation and compositionality in an artificial neural network. The ability to learn predicates from experience, to represent structures compositionally, and to extrapolate to unseen data offers an inroads to understanding and modeling the most complex human behaviors." @default.
- W2894810083 created "2018-10-12" @default.
- W2894810083 creator A5070044658 @default.
- W2894810083 creator A5074060464 @default.
- W2894810083 date "2018-10-02" @default.
- W2894810083 modified "2023-09-27" @default.
- W2894810083 title "Predicate learning in neural systems: Discovering latent generative structures." @default.
- W2894810083 cites W1571146030 @default.
- W2894810083 cites W1928882148 @default.
- W2894810083 cites W1966678693 @default.
- W2894810083 cites W1982786963 @default.
- W2894810083 cites W1986787497 @default.
- W2894810083 cites W1994335990 @default.
- W2894810083 cites W1995921430 @default.
- W2894810083 cites W1996404651 @default.
- W2894810083 cites W2003037938 @default.
- W2894810083 cites W2007283628 @default.
- W2894810083 cites W2011647584 @default.
- W2894810083 cites W2026799324 @default.
- W2894810083 cites W2093867260 @default.
- W2894810083 cites W2107139863 @default.
- W2894810083 cites W2119017831 @default.
- W2894810083 cites W2123713131 @default.
- W2894810083 cites W2127389037 @default.
- W2894810083 cites W2142029338 @default.
- W2894810083 cites W2145339207 @default.
- W2894810083 cites W2147336195 @default.
- W2894810083 cites W2148764920 @default.
- W2894810083 cites W2160819725 @default.
- W2894810083 cites W2164700406 @default.
- W2894810083 cites W2194321275 @default.
- W2894810083 cites W2195506630 @default.
- W2894810083 cites W2294349021 @default.
- W2894810083 cites W2592971502 @default.
- W2894810083 cites W2781474777 @default.
- W2894810083 cites W2805478747 @default.
- W2894810083 cites W2919115771 @default.
- W2894810083 cites W2963305465 @default.
- W2894810083 cites W3005002645 @default.
- W2894810083 hasPublicationYear "2018" @default.
- W2894810083 type Work @default.
- W2894810083 sameAs 2894810083 @default.
- W2894810083 citedByCount "0" @default.
- W2894810083 crossrefType "posted-content" @default.
- W2894810083 hasAuthorship W2894810083A5070044658 @default.
- W2894810083 hasAuthorship W2894810083A5074060464 @default.
- W2894810083 hasConcept C121375916 @default.
- W2894810083 hasConcept C140146324 @default.
- W2894810083 hasConcept C154945302 @default.
- W2894810083 hasConcept C15744967 @default.
- W2894810083 hasConcept C167966045 @default.
- W2894810083 hasConcept C188147891 @default.
- W2894810083 hasConcept C199360897 @default.
- W2894810083 hasConcept C39890363 @default.
- W2894810083 hasConcept C41008148 @default.
- W2894810083 hasConcept C50644808 @default.
- W2894810083 hasConceptScore W2894810083C121375916 @default.
- W2894810083 hasConceptScore W2894810083C140146324 @default.
- W2894810083 hasConceptScore W2894810083C154945302 @default.
- W2894810083 hasConceptScore W2894810083C15744967 @default.
- W2894810083 hasConceptScore W2894810083C167966045 @default.
- W2894810083 hasConceptScore W2894810083C188147891 @default.
- W2894810083 hasConceptScore W2894810083C199360897 @default.
- W2894810083 hasConceptScore W2894810083C39890363 @default.
- W2894810083 hasConceptScore W2894810083C41008148 @default.
- W2894810083 hasConceptScore W2894810083C50644808 @default.
- W2894810083 hasLocation W28948100831 @default.
- W2894810083 hasOpenAccess W2894810083 @default.
- W2894810083 hasPrimaryLocation W28948100831 @default.
- W2894810083 hasRelatedWork W1501002433 @default.
- W2894810083 hasRelatedWork W1565713682 @default.
- W2894810083 hasRelatedWork W1569813351 @default.
- W2894810083 hasRelatedWork W1950659143 @default.
- W2894810083 hasRelatedWork W1979593544 @default.
- W2894810083 hasRelatedWork W2003893062 @default.
- W2894810083 hasRelatedWork W2143623899 @default.
- W2894810083 hasRelatedWork W2224533248 @default.
- W2894810083 hasRelatedWork W2470855507 @default.
- W2894810083 hasRelatedWork W2801033965 @default.
- W2894810083 hasRelatedWork W2898365215 @default.
- W2894810083 hasRelatedWork W2945498739 @default.
- W2894810083 hasRelatedWork W2963525451 @default.
- W2894810083 hasRelatedWork W2972830298 @default.
- W2894810083 hasRelatedWork W3034854345 @default.
- W2894810083 hasRelatedWork W3113055895 @default.
- W2894810083 hasRelatedWork W3184018140 @default.
- W2894810083 hasRelatedWork W3186680487 @default.
- W2894810083 hasRelatedWork W3210837812 @default.
- W2894810083 hasRelatedWork W83529680 @default.
- W2894810083 isParatext "false" @default.
- W2894810083 isRetracted "false" @default.
- W2894810083 magId "2894810083" @default.
- W2894810083 workType "article" @default.