FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2002134846> ?p ?o ?g. }

• W2002134846 endingPage "140" @default.
• W2002134846 startingPage "117" @default.
• W2002134846 abstract "We consider the role of contextual guidance in learning and processing within multi-stream neural networks. Earlier work ([Kay and Phillips, 1994][Kay and Phillips, 1996]; [Phillips et al., 1995]) showed how the goals of feature discovery and associative learning could be fused within a single objective and made precise using information theory in such a way that local binary processors could extract a single feature that is coherent across streams. In this paper, we consider multi-unit local processors with multivariate binary outputs that enable a greater number of coherent features to be extracted. Using the Ising model, we define a class of information-theoretic objective functions and also local approximations and derive the learning rules in both cases. These rules have similarities to, and differences from, the celebrated BCM rule. Local and global versions of infomax appear as by-products of the general approach, as well as multivariate versions of coherent infomax. Focussing on the more biologically plausible local rules, we describe some computational experiments designed to investigate specific properties of the processors and the general approach. The main conclusions are: (1) the local methodology introduced in the paper has the required functionality. (2) Different units within the multi-unit processors learned to respond to different aspects of their receptive fields. (3) The units within each processor generally produced a distributed code in which the outputs were correlated and which was robust to damage; in the special case where the number of units available was only just sufficient to transmit the relevant information, a form of competitive learning was produced. (4) The contextual connections enabled the information correlated across streams to be extracted and, by improving feature detection with weak or noisy inputs, they played a useful role in short-term processing and in improving generalization. (5) The methodology allows the statistical associations between distributed self-organizing population codes to be learned." @default.
• W2002134846 created "2016-06-24" @default.
• W2002134846 creator A5042066719 @default.
• W2002134846 creator A5059369445 @default.
• W2002134846 creator A5071485738 @default.
• W2002134846 date "1998-01-01" @default.
• W2002134846 modified "2023-10-16" @default.
• W2002134846 title "Contextually guided unsupervised learning using local multivariate binary processors" @default.
• W2002134846 cites W1248076745 @default.
• W2002134846 cites W1601361876 @default.
• W2002134846 cites W1971074050 @default.
• W2002134846 cites W1981268965 @default.
• W2002134846 cites W1988773134 @default.
• W2002134846 cites W2003073069 @default.
• W2002134846 cites W2015931493 @default.
• W2002134846 cites W2020999234 @default.
• W2002134846 cites W2022941364 @default.
• W2002134846 cites W2024981360 @default.
• W2002134846 cites W2025341678 @default.
• W2002134846 cites W2029346512 @default.
• W2002134846 cites W2037395945 @default.
• W2002134846 cites W2063971957 @default.
• W2002134846 cites W2067415178 @default.
• W2002134846 cites W2068674173 @default.
• W2002134846 cites W2107484626 @default.
• W2002134846 cites W2122925692 @default.
• W2002134846 cites W2128084896 @default.
• W2002134846 cites W2129700304 @default.
• W2002134846 cites W2134858096 @default.
• W2002134846 cites W2136660863 @default.
• W2002134846 cites W2149316826 @default.
• W2002134846 cites W2166924410 @default.
• W2002134846 cites W2172513721 @default.
• W2002134846 cites W4230610536 @default.
• W2002134846 cites W4232801517 @default.
• W2002134846 cites W4240035482 @default.
• W2002134846 cites W4301861531 @default.
• W2002134846 doi "https://doi.org/10.1016/s0893-6080(97)00110-x" @default.
• W2002134846 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/12662852" @default.
• W2002134846 hasPublicationYear "1998" @default.
• W2002134846 type Work @default.
• W2002134846 sameAs 2002134846 @default.
• W2002134846 citedByCount "76" @default.
• W2002134846 countsByYear W20021348462012 @default.
• W2002134846 countsByYear W20021348462013 @default.
• W2002134846 countsByYear W20021348462014 @default.
• W2002134846 countsByYear W20021348462015 @default.
• W2002134846 countsByYear W20021348462016 @default.
• W2002134846 countsByYear W20021348462017 @default.
• W2002134846 countsByYear W20021348462018 @default.
• W2002134846 countsByYear W20021348462019 @default.
• W2002134846 countsByYear W20021348462020 @default.
• W2002134846 countsByYear W20021348462022 @default.
• W2002134846 countsByYear W20021348462023 @default.
• W2002134846 crossrefType "journal-article" @default.
• W2002134846 hasAuthorship W2002134846A5042066719 @default.
• W2002134846 hasAuthorship W2002134846A5059369445 @default.
• W2002134846 hasAuthorship W2002134846A5071485738 @default.
• W2002134846 hasBestOaLocation W20021348462 @default.
• W2002134846 hasConcept C119857082 @default.
• W2002134846 hasConcept C120317606 @default.
• W2002134846 hasConcept C127162648 @default.
• W2002134846 hasConcept C138885662 @default.
• W2002134846 hasConcept C153180895 @default.
• W2002134846 hasConcept C153402090 @default.
• W2002134846 hasConcept C154945302 @default.
• W2002134846 hasConcept C159423971 @default.
• W2002134846 hasConcept C161584116 @default.
• W2002134846 hasConcept C177264268 @default.
• W2002134846 hasConcept C199360897 @default.
• W2002134846 hasConcept C202444582 @default.
• W2002134846 hasConcept C2776401178 @default.
• W2002134846 hasConcept C2776760102 @default.
• W2002134846 hasConcept C31258907 @default.
• W2002134846 hasConcept C33923547 @default.
• W2002134846 hasConcept C41008148 @default.
• W2002134846 hasConcept C41895202 @default.
• W2002134846 hasConcept C48372109 @default.
• W2002134846 hasConcept C50644808 @default.
• W2002134846 hasConcept C8038995 @default.
• W2002134846 hasConcept C80444323 @default.
• W2002134846 hasConcept C94375191 @default.
• W2002134846 hasConceptScore W2002134846C119857082 @default.
• W2002134846 hasConceptScore W2002134846C120317606 @default.
• W2002134846 hasConceptScore W2002134846C127162648 @default.
• W2002134846 hasConceptScore W2002134846C138885662 @default.
• W2002134846 hasConceptScore W2002134846C153180895 @default.
• W2002134846 hasConceptScore W2002134846C153402090 @default.
• W2002134846 hasConceptScore W2002134846C154945302 @default.
• W2002134846 hasConceptScore W2002134846C159423971 @default.
• W2002134846 hasConceptScore W2002134846C161584116 @default.
• W2002134846 hasConceptScore W2002134846C177264268 @default.
• W2002134846 hasConceptScore W2002134846C199360897 @default.
• W2002134846 hasConceptScore W2002134846C202444582 @default.
• W2002134846 hasConceptScore W2002134846C2776401178 @default.
• W2002134846 hasConceptScore W2002134846C2776760102 @default.
• W2002134846 hasConceptScore W2002134846C31258907 @default.
• W2002134846 hasConceptScore W2002134846C33923547 @default.

• next