Matches in SemOpenAlex for { <https://semopenalex.org/work/W2059932101> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2059932101 abstract "An unsupervised learning algorithm for a stochastic recurrent neural network based on the Boltzmann Machine architecture is formulated in this paper. The maximization of the mutual information between the stochastic output neurons and the clamped inputs is used as an unsupervised criterion for training the network. The resulting learning rule contains two terms corresponding to Hebbian and anti-Hebbian learning. It is interesting that these two terms are weighted by the amount of information transmitted in the learning synapse, giving an information-theoretic interpretation of the proportionality constant of Hebb's biological rule. The anti-Hebbian term, which can be interpreted as a forgetting function, supports the optimal coding. In this way, optimal nonlinear and recurrent implementations of data compression of Boolean patterns are obtained. As an example, the encoder problem is simulated and trained in an unsupervised way in a one layer network. Compression of non-uniform distributed binary data is i..." @default.
- W2059932101 created "2016-06-24" @default.
- W2059932101 creator A5047963275 @default.
- W2059932101 creator A5079902276 @default.
- W2059932101 date "1995-01-01" @default.
- W2059932101 modified "2023-09-23" @default.
- W2059932101 title "Unsupervised learning for Boltzman Machines" @default.
- W2059932101 cites W1965498468 @default.
- W2059932101 cites W1967337726 @default.
- W2059932101 cites W1979191599 @default.
- W2059932101 cites W1983272724 @default.
- W2059932101 cites W1995875735 @default.
- W2059932101 cites W2042492924 @default.
- W2059932101 cites W2087489167 @default.
- W2059932101 cites W2122925692 @default.
- W2059932101 cites W2123806929 @default.
- W2059932101 cites W2144914634 @default.
- W2059932101 cites W2151351982 @default.
- W2059932101 cites W2202951610 @default.
- W2059932101 doi "https://doi.org/10.1088/0954-898x_6_3_009" @default.
- W2059932101 hasPublicationYear "1995" @default.
- W2059932101 type Work @default.
- W2059932101 sameAs 2059932101 @default.
- W2059932101 citedByCount "1" @default.
- W2059932101 crossrefType "journal-article" @default.
- W2059932101 hasAuthorship W2059932101A5047963275 @default.
- W2059932101 hasAuthorship W2059932101A5079902276 @default.
- W2059932101 hasConcept C111437709 @default.
- W2059932101 hasConcept C117765406 @default.
- W2059932101 hasConcept C119857082 @default.
- W2059932101 hasConcept C120822770 @default.
- W2059932101 hasConcept C126255220 @default.
- W2059932101 hasConcept C152139883 @default.
- W2059932101 hasConcept C154945302 @default.
- W2059932101 hasConcept C17061570 @default.
- W2059932101 hasConcept C192576344 @default.
- W2059932101 hasConcept C2776330181 @default.
- W2059932101 hasConcept C2779127903 @default.
- W2059932101 hasConcept C33923547 @default.
- W2059932101 hasConcept C41008148 @default.
- W2059932101 hasConcept C46421273 @default.
- W2059932101 hasConcept C50644808 @default.
- W2059932101 hasConcept C8038995 @default.
- W2059932101 hasConcept C80444323 @default.
- W2059932101 hasConcept C97108695 @default.
- W2059932101 hasConceptScore W2059932101C111437709 @default.
- W2059932101 hasConceptScore W2059932101C117765406 @default.
- W2059932101 hasConceptScore W2059932101C119857082 @default.
- W2059932101 hasConceptScore W2059932101C120822770 @default.
- W2059932101 hasConceptScore W2059932101C126255220 @default.
- W2059932101 hasConceptScore W2059932101C152139883 @default.
- W2059932101 hasConceptScore W2059932101C154945302 @default.
- W2059932101 hasConceptScore W2059932101C17061570 @default.
- W2059932101 hasConceptScore W2059932101C192576344 @default.
- W2059932101 hasConceptScore W2059932101C2776330181 @default.
- W2059932101 hasConceptScore W2059932101C2779127903 @default.
- W2059932101 hasConceptScore W2059932101C33923547 @default.
- W2059932101 hasConceptScore W2059932101C41008148 @default.
- W2059932101 hasConceptScore W2059932101C46421273 @default.
- W2059932101 hasConceptScore W2059932101C50644808 @default.
- W2059932101 hasConceptScore W2059932101C8038995 @default.
- W2059932101 hasConceptScore W2059932101C80444323 @default.
- W2059932101 hasConceptScore W2059932101C97108695 @default.
- W2059932101 hasLocation W20599321011 @default.
- W2059932101 hasOpenAccess W2059932101 @default.
- W2059932101 hasPrimaryLocation W20599321011 @default.
- W2059932101 hasRelatedWork W1492899839 @default.
- W2059932101 hasRelatedWork W1538134366 @default.
- W2059932101 hasRelatedWork W1591603520 @default.
- W2059932101 hasRelatedWork W1899154215 @default.
- W2059932101 hasRelatedWork W1919060698 @default.
- W2059932101 hasRelatedWork W1983106178 @default.
- W2059932101 hasRelatedWork W1986178142 @default.
- W2059932101 hasRelatedWork W2062690289 @default.
- W2059932101 hasRelatedWork W2068495893 @default.
- W2059932101 hasRelatedWork W2080958785 @default.
- W2059932101 hasRelatedWork W2101856428 @default.
- W2059932101 hasRelatedWork W2104196470 @default.
- W2059932101 hasRelatedWork W2132511476 @default.
- W2059932101 hasRelatedWork W2149594649 @default.
- W2059932101 hasRelatedWork W2159916088 @default.
- W2059932101 hasRelatedWork W2493778867 @default.
- W2059932101 hasRelatedWork W2766455950 @default.
- W2059932101 hasRelatedWork W2962899068 @default.
- W2059932101 hasRelatedWork W3102303919 @default.
- W2059932101 hasRelatedWork W32001702 @default.
- W2059932101 isParatext "false" @default.
- W2059932101 isRetracted "false" @default.
- W2059932101 magId "2059932101" @default.
- W2059932101 workType "article" @default.