Matches in SemOpenAlex for { <https://semopenalex.org/work/W203205979> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W203205979 abstract "The brain's capacity for learning, adaptation and intelligent behaviour is unmatched by any artificial system. By modelling what we know of brain function we hope to gain further understanding of how the brain accomplishes this, as well as to build new systems which exhibit brain-like abilities. There is no doubt that the facilitator of intelligent adaptive behaviour within the brain is the cortex. Despite its myriad functional roles, the cortex of the brain is remarkably uniform in overall structure, even regarding frontal (largely concerned with motor control and planning) and posterior (largely concerned with perception) cortices. This suggests that similar learning processes are at work across all cortical functional domains. This work presents a working cortical model called Cognac - the 'Cognition in Action' neural network - which models the macroscopic structure of the mammalian cortex, including perceptual (posterior) and motor (anterior) processing hierarchies and the many feedforward and feedback intra- and interconnections. Cognac utilises two novel, biologically-plausible learning algorithms, the first for training of the feedforward connections (and called here Biologically-Plausible Hebbian Learning or BP-Hebb), and the second for training of the feedback connections (called here Expectation Learning). BP-Hebb performs self-organised hierarchical feature extraction for the perceptual cortex, and with slight modifications also performs what is called here 'motor feature abstraction' for the motor cortex. Motor feature abstraction is a self-organised hierarchical temporal pattern recognition scheme which is capable of 'chunking' - the recognition of identical repeated subsequences within two or more differing supersequences - the ability for which has never before been demonstrated using any unsupervised learning algorithm. Expectation Learning uses the feedback connections to predict incoming stimuli from top-down representations. Features on the input which have the largest discrepancy between the top-down expectation and bottom-up incoming stimulus equate to those features which are least-well represented by the perceptual hierarchy, and as such are used to guide further learning by the network. Cognac exhibits interesting behaviour as it learns, with no external control, to look over simple images of digitised hand-written numerals. Some thoughts further exploring the mechanisms of cognition are presented in the context of this cortical model." @default.
- W203205979 created "2016-06-24" @default.
- W203205979 creator A5091012593 @default.
- W203205979 date "2001-01-01" @default.
- W203205979 modified "2023-09-22" @default.
- W203205979 title "A situated cortical model exhibiting attention, learning ane memory : implications for cognition" @default.
- W203205979 hasPublicationYear "2001" @default.
- W203205979 type Work @default.
- W203205979 sameAs 203205979 @default.
- W203205979 citedByCount "0" @default.
- W203205979 crossrefType "journal-article" @default.
- W203205979 hasAuthorship W203205979A5091012593 @default.
- W203205979 hasConcept C105702510 @default.
- W203205979 hasConcept C111437709 @default.
- W203205979 hasConcept C127413603 @default.
- W203205979 hasConcept C133731056 @default.
- W203205979 hasConcept C140530291 @default.
- W203205979 hasConcept C154945302 @default.
- W203205979 hasConcept C15744967 @default.
- W203205979 hasConcept C169760540 @default.
- W203205979 hasConcept C169900460 @default.
- W203205979 hasConcept C188147891 @default.
- W203205979 hasConcept C203357204 @default.
- W203205979 hasConcept C24998067 @default.
- W203205979 hasConcept C26760741 @default.
- W203205979 hasConcept C2778373776 @default.
- W203205979 hasConcept C2779534489 @default.
- W203205979 hasConcept C38858127 @default.
- W203205979 hasConcept C41008148 @default.
- W203205979 hasConcept C50644808 @default.
- W203205979 hasConcept C71924100 @default.
- W203205979 hasConceptScore W203205979C105702510 @default.
- W203205979 hasConceptScore W203205979C111437709 @default.
- W203205979 hasConceptScore W203205979C127413603 @default.
- W203205979 hasConceptScore W203205979C133731056 @default.
- W203205979 hasConceptScore W203205979C140530291 @default.
- W203205979 hasConceptScore W203205979C154945302 @default.
- W203205979 hasConceptScore W203205979C15744967 @default.
- W203205979 hasConceptScore W203205979C169760540 @default.
- W203205979 hasConceptScore W203205979C169900460 @default.
- W203205979 hasConceptScore W203205979C188147891 @default.
- W203205979 hasConceptScore W203205979C203357204 @default.
- W203205979 hasConceptScore W203205979C24998067 @default.
- W203205979 hasConceptScore W203205979C26760741 @default.
- W203205979 hasConceptScore W203205979C2778373776 @default.
- W203205979 hasConceptScore W203205979C2779534489 @default.
- W203205979 hasConceptScore W203205979C38858127 @default.
- W203205979 hasConceptScore W203205979C41008148 @default.
- W203205979 hasConceptScore W203205979C50644808 @default.
- W203205979 hasConceptScore W203205979C71924100 @default.
- W203205979 hasLocation W2032059791 @default.
- W203205979 hasOpenAccess W203205979 @default.
- W203205979 hasPrimaryLocation W2032059791 @default.
- W203205979 hasRelatedWork W1944649656 @default.
- W203205979 hasRelatedWork W2005492971 @default.
- W203205979 hasRelatedWork W2006039742 @default.
- W203205979 hasRelatedWork W2042038373 @default.
- W203205979 hasRelatedWork W2050981541 @default.
- W203205979 hasRelatedWork W2057018347 @default.
- W203205979 hasRelatedWork W2131140847 @default.
- W203205979 hasRelatedWork W2148741590 @default.
- W203205979 hasRelatedWork W2472932211 @default.
- W203205979 hasRelatedWork W2592971502 @default.
- W203205979 hasRelatedWork W2599566697 @default.
- W203205979 hasRelatedWork W2965371151 @default.
- W203205979 hasRelatedWork W3005132916 @default.
- W203205979 hasRelatedWork W3015305869 @default.
- W203205979 hasRelatedWork W3039556919 @default.
- W203205979 hasRelatedWork W3096426565 @default.
- W203205979 hasRelatedWork W3136669519 @default.
- W203205979 hasRelatedWork W3161579287 @default.
- W203205979 hasRelatedWork W3171682952 @default.
- W203205979 hasRelatedWork W3184928878 @default.
- W203205979 isParatext "false" @default.
- W203205979 isRetracted "false" @default.
- W203205979 magId "203205979" @default.
- W203205979 workType "article" @default.