Matches in SemOpenAlex for { <https://semopenalex.org/work/W2052981568> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2052981568 endingPage "1070" @default.
- W2052981568 startingPage "1061" @default.
- W2052981568 abstract "The dynamics of a probabilistic neural network is characterized by the distribution ensuremath{nu}(x'ensuremath{Vert}x) of successor states x' of an arbitrary state x of the network. A prescribed memory or behavior pattern is represented in terms of an ordered sequence of network states ${mathit{x}}^{(1)}$,${mathit{x}}^{(2)}$,...,${mathit{x}}^{(mathit{l})}$. A successful procedure for learning this pattern must modify the neuronal interactions in such a way that the dynamical successor of ${mathit{x}}^{(mathit{s})}$ is likely to be ${mathit{x}}^{(mathit{s}+1)}$, with ${mathit{x}}^{(mathit{l}+1)}$=${mathit{x}}^{(1)}$. The relative entropy G of the probability distribution ${mathrm{ensuremath{delta}}}_{mathit{x}}^{(mathit{s}+1)}$,x' concentrated at the desired successor state, evaluated with respect to the dynamical distribution ensuremath{nu}(x'ensuremath{Vert}${mathit{x}}^{(mathit{s})}$), is used to quantify this criterion, by providing a measure of the distance between actual and ideal probability distributions. Minimization of G subject to appropriate resource constraints leads to ``optimal'' learning rules for pairwise and higher-order neuronal interactions. The degree to which optimality is approached by simple learning rules in current use is considered, and it is found, in particular, that the algorithm adopted in the Hopfield model is more effective in minimizing G than the original Hebb law." @default.
- W2052981568 created "2016-06-24" @default.
- W2052981568 creator A5025228488 @default.
- W2052981568 creator A5061662846 @default.
- W2052981568 creator A5079361224 @default.
- W2052981568 date "1991-01-01" @default.
- W2052981568 modified "2023-09-23" @default.
- W2052981568 title "Relative entropy and learning rules" @default.
- W2052981568 cites W1884390770 @default.
- W2052981568 cites W1963551978 @default.
- W2052981568 cites W1967011375 @default.
- W2052981568 cites W1967337726 @default.
- W2052981568 cites W1995341919 @default.
- W2052981568 cites W1997161930 @default.
- W2052981568 cites W2007085969 @default.
- W2052981568 cites W2032765606 @default.
- W2052981568 cites W2037529930 @default.
- W2052981568 cites W2040598998 @default.
- W2052981568 cites W2042492924 @default.
- W2052981568 cites W2043014754 @default.
- W2052981568 cites W2091172266 @default.
- W2052981568 cites W2128084896 @default.
- W2052981568 cites W4211128390 @default.
- W2052981568 cites W4212941528 @default.
- W2052981568 cites W4241400578 @default.
- W2052981568 cites W4300402905 @default.
- W2052981568 doi "https://doi.org/10.1103/physreva.43.1061" @default.
- W2052981568 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/9905122" @default.
- W2052981568 hasPublicationYear "1991" @default.
- W2052981568 type Work @default.
- W2052981568 sameAs 2052981568 @default.
- W2052981568 citedByCount "16" @default.
- W2052981568 countsByYear W20529815682014 @default.
- W2052981568 countsByYear W20529815682016 @default.
- W2052981568 countsByYear W20529815682017 @default.
- W2052981568 countsByYear W20529815682019 @default.
- W2052981568 countsByYear W20529815682020 @default.
- W2052981568 countsByYear W20529815682022 @default.
- W2052981568 countsByYear W20529815682023 @default.
- W2052981568 crossrefType "journal-article" @default.
- W2052981568 hasAuthorship W2052981568A5025228488 @default.
- W2052981568 hasAuthorship W2052981568A5061662846 @default.
- W2052981568 hasAuthorship W2052981568A5079361224 @default.
- W2052981568 hasConcept C10138342 @default.
- W2052981568 hasConcept C105795698 @default.
- W2052981568 hasConcept C110121322 @default.
- W2052981568 hasConcept C114614502 @default.
- W2052981568 hasConcept C121332964 @default.
- W2052981568 hasConcept C121864883 @default.
- W2052981568 hasConcept C134306372 @default.
- W2052981568 hasConcept C149441793 @default.
- W2052981568 hasConcept C162324750 @default.
- W2052981568 hasConcept C182306322 @default.
- W2052981568 hasConcept C33923547 @default.
- W2052981568 hasConcept C75306776 @default.
- W2052981568 hasConceptScore W2052981568C10138342 @default.
- W2052981568 hasConceptScore W2052981568C105795698 @default.
- W2052981568 hasConceptScore W2052981568C110121322 @default.
- W2052981568 hasConceptScore W2052981568C114614502 @default.
- W2052981568 hasConceptScore W2052981568C121332964 @default.
- W2052981568 hasConceptScore W2052981568C121864883 @default.
- W2052981568 hasConceptScore W2052981568C134306372 @default.
- W2052981568 hasConceptScore W2052981568C149441793 @default.
- W2052981568 hasConceptScore W2052981568C162324750 @default.
- W2052981568 hasConceptScore W2052981568C182306322 @default.
- W2052981568 hasConceptScore W2052981568C33923547 @default.
- W2052981568 hasConceptScore W2052981568C75306776 @default.
- W2052981568 hasIssue "2" @default.
- W2052981568 hasLocation W20529815681 @default.
- W2052981568 hasLocation W20529815682 @default.
- W2052981568 hasOpenAccess W2052981568 @default.
- W2052981568 hasPrimaryLocation W20529815681 @default.
- W2052981568 hasRelatedWork W1522602455 @default.
- W2052981568 hasRelatedWork W1975860297 @default.
- W2052981568 hasRelatedWork W1978883506 @default.
- W2052981568 hasRelatedWork W2000218587 @default.
- W2052981568 hasRelatedWork W2106535591 @default.
- W2052981568 hasRelatedWork W2461356222 @default.
- W2052981568 hasRelatedWork W2950880503 @default.
- W2052981568 hasRelatedWork W2952853187 @default.
- W2052981568 hasRelatedWork W3099184912 @default.
- W2052981568 hasRelatedWork W4297568945 @default.
- W2052981568 hasVolume "43" @default.
- W2052981568 isParatext "false" @default.
- W2052981568 isRetracted "false" @default.
- W2052981568 magId "2052981568" @default.
- W2052981568 workType "article" @default.