Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208686557> ?p ?o ?g. }
- W3208686557 endingPage "126716" @default.
- W3208686557 startingPage "126716" @default.
- W3208686557 abstract "The formal equivalence between the Hopfield network (HN) and the Boltzmann Machine (BM) has been well established in the context of random, unstructured and unbiased patterns to be retrieved and recognised. Here we extend this equivalence to the case of “biased” patterns, that is patterns which display an unbalanced count of positive neurons/pixels: starting from previous results of the bias paradigm for the HN, we construct the BM’s equivalent Hamiltonian introducing a constraint parameter for the bias correction. We show analytically and numerically that the parameters suggested by equivalence are fixed points under contrastive divergence evolution when exposed to a dataset of blurred examples of each pattern, also enjoying large basins of attraction when the model suffers of a noisy initialisation. These results are also shown to be robust against increasing storage of the models, and increasing bias in the reference patterns. This picture, together with analytical derivation of HN’s phase diagram via self-consistency equations, allows us to enhance our mathematical control on BM’s performance when approaching more realistic datasets." @default.
- W3208686557 created "2021-11-08" @default.
- W3208686557 creator A5041121941 @default.
- W3208686557 creator A5041457930 @default.
- W3208686557 creator A5090549161 @default.
- W3208686557 date "2022-02-01" @default.
- W3208686557 modified "2023-09-24" @default.
- W3208686557 title "Storing, learning and retrieving biased patterns" @default.
- W3208686557 cites W1893876825 @default.
- W3208686557 cites W1957216077 @default.
- W3208686557 cites W1965496542 @default.
- W3208686557 cites W1966240450 @default.
- W3208686557 cites W1973584826 @default.
- W3208686557 cites W1976022939 @default.
- W3208686557 cites W1984431842 @default.
- W3208686557 cites W2015945804 @default.
- W3208686557 cites W2022915866 @default.
- W3208686557 cites W2026057272 @default.
- W3208686557 cites W2042492924 @default.
- W3208686557 cites W2055864556 @default.
- W3208686557 cites W2064630666 @default.
- W3208686557 cites W2069129925 @default.
- W3208686557 cites W2080792322 @default.
- W3208686557 cites W2083242503 @default.
- W3208686557 cites W2115818372 @default.
- W3208686557 cites W2116064496 @default.
- W3208686557 cites W2124468981 @default.
- W3208686557 cites W2125150881 @default.
- W3208686557 cites W2128084896 @default.
- W3208686557 cites W2156740722 @default.
- W3208686557 cites W2161410247 @default.
- W3208686557 cites W2556341799 @default.
- W3208686557 cites W2567167069 @default.
- W3208686557 cites W2593807178 @default.
- W3208686557 cites W2982581043 @default.
- W3208686557 cites W3027269453 @default.
- W3208686557 cites W3099406601 @default.
- W3208686557 cites W3100464551 @default.
- W3208686557 cites W3101875373 @default.
- W3208686557 cites W3116923736 @default.
- W3208686557 cites W3134073469 @default.
- W3208686557 cites W3156867879 @default.
- W3208686557 cites W3173484311 @default.
- W3208686557 cites W4376453414 @default.
- W3208686557 cites W3147726452 @default.
- W3208686557 doi "https://doi.org/10.1016/j.amc.2021.126716" @default.
- W3208686557 hasPublicationYear "2022" @default.
- W3208686557 type Work @default.
- W3208686557 sameAs 3208686557 @default.
- W3208686557 citedByCount "5" @default.
- W3208686557 countsByYear W32086865572021 @default.
- W3208686557 countsByYear W32086865572022 @default.
- W3208686557 countsByYear W32086865572023 @default.
- W3208686557 crossrefType "journal-article" @default.
- W3208686557 hasAuthorship W3208686557A5041121941 @default.
- W3208686557 hasAuthorship W3208686557A5041457930 @default.
- W3208686557 hasAuthorship W3208686557A5090549161 @default.
- W3208686557 hasConcept C11413529 @default.
- W3208686557 hasConcept C118615104 @default.
- W3208686557 hasConcept C138885662 @default.
- W3208686557 hasConcept C151730666 @default.
- W3208686557 hasConcept C154945302 @default.
- W3208686557 hasConcept C160633673 @default.
- W3208686557 hasConcept C192576344 @default.
- W3208686557 hasConcept C207390915 @default.
- W3208686557 hasConcept C2524010 @default.
- W3208686557 hasConcept C2776036281 @default.
- W3208686557 hasConcept C2779343474 @default.
- W3208686557 hasConcept C2780069185 @default.
- W3208686557 hasConcept C28826006 @default.
- W3208686557 hasConcept C33923547 @default.
- W3208686557 hasConcept C41008148 @default.
- W3208686557 hasConcept C41895202 @default.
- W3208686557 hasConcept C50644808 @default.
- W3208686557 hasConcept C80444323 @default.
- W3208686557 hasConcept C86803240 @default.
- W3208686557 hasConceptScore W3208686557C11413529 @default.
- W3208686557 hasConceptScore W3208686557C118615104 @default.
- W3208686557 hasConceptScore W3208686557C138885662 @default.
- W3208686557 hasConceptScore W3208686557C151730666 @default.
- W3208686557 hasConceptScore W3208686557C154945302 @default.
- W3208686557 hasConceptScore W3208686557C160633673 @default.
- W3208686557 hasConceptScore W3208686557C192576344 @default.
- W3208686557 hasConceptScore W3208686557C207390915 @default.
- W3208686557 hasConceptScore W3208686557C2524010 @default.
- W3208686557 hasConceptScore W3208686557C2776036281 @default.
- W3208686557 hasConceptScore W3208686557C2779343474 @default.
- W3208686557 hasConceptScore W3208686557C2780069185 @default.
- W3208686557 hasConceptScore W3208686557C28826006 @default.
- W3208686557 hasConceptScore W3208686557C33923547 @default.
- W3208686557 hasConceptScore W3208686557C41008148 @default.
- W3208686557 hasConceptScore W3208686557C41895202 @default.
- W3208686557 hasConceptScore W3208686557C50644808 @default.
- W3208686557 hasConceptScore W3208686557C80444323 @default.
- W3208686557 hasConceptScore W3208686557C86803240 @default.
- W3208686557 hasFunder F4320322510 @default.
- W3208686557 hasLocation W32086865571 @default.
- W3208686557 hasOpenAccess W3208686557 @default.