FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2036759514> ?p ?o ?g. }

• W2036759514 endingPage "11084" @default.
• W2036759514 startingPage "11079" @default.
• W2036759514 abstract "Recent experimental studies indicate that synaptic changes induced by neuronal activity are discrete jumps between a small number of stable states. Learning in systems with discrete synapses is known to be a computationally hard problem. Here, we study a neurobiologically plausible on-line learning algorithm that derives from belief propagation algorithms. We show that it performs remarkably well in a model neuron with binary synapses, and a finite number of hidden states per synapse, that has to learn a random classification task. Such a system is able to learn a number of associations close to the theoretical limit in time that is sublinear in system size. This is to our knowledge the first on-line algorithm that is able to achieve efficiently a finite number of patterns learned per binary synapse. Furthermore, we show that performance is optimal for a finite number of hidden states that becomes very small for sparse coding. The algorithm is similar to the standard perceptron learning algorithm, with an additional rule for synaptic transitions that occur only if a currently presented pattern is barely correct. In this case, the synaptic changes are metaplastic only (change in hidden states and not in actual synaptic state), stabilizing the synapse in its current state. Finally, we show that a system with two visible states and K hidden states is much more robust to noise than a system with K visible states. We suggest that this rule is sufficiently simple to be easily implemented by neurobiological systems or in hardware." @default.
• W2036759514 created "2016-06-24" @default.
• W2036759514 creator A5028083013 @default.
• W2036759514 creator A5041685522 @default.
• W2036759514 creator A5047235486 @default.
• W2036759514 creator A5067371775 @default.
• W2036759514 date "2007-06-26" @default.
• W2036759514 modified "2023-10-18" @default.
• W2036759514 title "Efficient supervised learning in networks with binary synapses" @default.
• W2036759514 cites W1518885151 @default.
• W2036759514 cites W1967272760 @default.
• W2036759514 cites W196871588 @default.
• W2036759514 cites W1978730538 @default.
• W2036759514 cites W1980130379 @default.
• W2036759514 cites W1994435842 @default.
• W2036759514 cites W2002193713 @default.
• W2036759514 cites W2002249797 @default.
• W2036759514 cites W2033606703 @default.
• W2036759514 cites W2047966157 @default.
• W2036759514 cites W2060910814 @default.
• W2036759514 cites W2080782191 @default.
• W2036759514 cites W2082622165 @default.
• W2036759514 cites W2083910902 @default.
• W2036759514 cites W2085138324 @default.
• W2036759514 cites W2092643070 @default.
• W2036759514 cites W2101222204 @default.
• W2036759514 cites W2107524792 @default.
• W2036759514 cites W2129386380 @default.
• W2036759514 cites W2133667940 @default.
• W2036759514 cites W2155051950 @default.
• W2036759514 cites W2164301806 @default.
• W2036759514 cites W2950654313 @default.
• W2036759514 cites W67367170 @default.
• W2036759514 doi "https://doi.org/10.1073/pnas.0700324104" @default.
• W2036759514 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/1904114" @default.
• W2036759514 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/17581884" @default.
• W2036759514 hasPublicationYear "2007" @default.
• W2036759514 type Work @default.
• W2036759514 sameAs 2036759514 @default.
• W2036759514 citedByCount "98" @default.
• W2036759514 countsByYear W20367595142012 @default.
• W2036759514 countsByYear W20367595142013 @default.
• W2036759514 countsByYear W20367595142014 @default.
• W2036759514 countsByYear W20367595142015 @default.
• W2036759514 countsByYear W20367595142016 @default.
• W2036759514 countsByYear W20367595142017 @default.
• W2036759514 countsByYear W20367595142018 @default.
• W2036759514 countsByYear W20367595142019 @default.
• W2036759514 countsByYear W20367595142020 @default.
• W2036759514 countsByYear W20367595142021 @default.
• W2036759514 countsByYear W20367595142022 @default.
• W2036759514 countsByYear W20367595142023 @default.
• W2036759514 crossrefType "journal-article" @default.
• W2036759514 hasAuthorship W2036759514A5028083013 @default.
• W2036759514 hasAuthorship W2036759514A5041685522 @default.
• W2036759514 hasAuthorship W2036759514A5047235486 @default.
• W2036759514 hasAuthorship W2036759514A5067371775 @default.
• W2036759514 hasBestOaLocation W20367595144 @default.
• W2036759514 hasConcept C11413529 @default.
• W2036759514 hasConcept C127445978 @default.
• W2036759514 hasConcept C153180895 @default.
• W2036759514 hasConcept C154945302 @default.
• W2036759514 hasConcept C169760540 @default.
• W2036759514 hasConcept C2779127903 @default.
• W2036759514 hasConcept C33923547 @default.
• W2036759514 hasConcept C41008148 @default.
• W2036759514 hasConcept C48372109 @default.
• W2036759514 hasConcept C50644808 @default.
• W2036759514 hasConcept C86803240 @default.
• W2036759514 hasConcept C94375191 @default.
• W2036759514 hasConceptScore W2036759514C11413529 @default.
• W2036759514 hasConceptScore W2036759514C127445978 @default.
• W2036759514 hasConceptScore W2036759514C153180895 @default.
• W2036759514 hasConceptScore W2036759514C154945302 @default.
• W2036759514 hasConceptScore W2036759514C169760540 @default.
• W2036759514 hasConceptScore W2036759514C2779127903 @default.
• W2036759514 hasConceptScore W2036759514C33923547 @default.
• W2036759514 hasConceptScore W2036759514C41008148 @default.
• W2036759514 hasConceptScore W2036759514C48372109 @default.
• W2036759514 hasConceptScore W2036759514C50644808 @default.
• W2036759514 hasConceptScore W2036759514C86803240 @default.
• W2036759514 hasConceptScore W2036759514C94375191 @default.
• W2036759514 hasIssue "26" @default.
• W2036759514 hasLocation W20367595141 @default.
• W2036759514 hasLocation W20367595142 @default.
• W2036759514 hasLocation W20367595143 @default.
• W2036759514 hasLocation W20367595144 @default.
• W2036759514 hasLocation W20367595145 @default.
• W2036759514 hasLocation W20367595146 @default.
• W2036759514 hasLocation W20367595147 @default.
• W2036759514 hasOpenAccess W2036759514 @default.
• W2036759514 hasPrimaryLocation W20367595141 @default.
• W2036759514 hasRelatedWork W1573182123 @default.
• W2036759514 hasRelatedWork W1982750869 @default.
• W2036759514 hasRelatedWork W1984922432 @default.
• W2036759514 hasRelatedWork W2086348228 @default.
• W2036759514 hasRelatedWork W2362198218 @default.
• W2036759514 hasRelatedWork W2373011427 @default.

• next