FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963208784> ?p ?o ?g. }

• W2963208784 endingPage "40" @default.
• W2963208784 startingPage "24" @default.
• W2963208784 abstract "The standard Hopfield model for associative neural networks accounts for biological Hebbian learning and acts as the harmonic oscillator for pattern recognition, however its maximal storage capacity is α∼0.14, far from the theoretical bound for symmetric networks, i.e. α=1. Inspired by sleeping and dreaming mechanisms in mammal brains, we propose an extension of this model displaying the standard on-line (awake) learning mechanism (that allows the storage of external information in terms of patterns) and an off-line (sleep) unlearning&consolidating mechanism (that allows spurious-pattern removal and pure-pattern reinforcement): this obtained daily prescription is able to saturate the theoretical bound α=1, remaining also extremely robust against thermal noise. The emergent neural and synaptic features are analyzed both analytically and numerically. In particular, beyond obtaining a phase diagram for neural dynamics, we focus on synaptic plasticity and we give explicit prescriptions on the temporal evolution of the synaptic matrix. We analytically prove that our algorithm makes the Hebbian kernel converge with high probability to the projection matrix built over the pure stored patterns. Furthermore, we obtain a sharp and explicit estimate for the sleep rate in order to ensure such a convergence. Finally, we run extensive numerical simulations (mainly Monte Carlo sampling) to check the approximations underlying the analytical investigations (e.g., we developed the whole theory at the so called replica-symmetric level, as standard in the Amit-Gutfreund-Sompolinsky reference framework) and possible finite-size effects, finding overall full agreement with the theory." @default.
• W2963208784 created "2019-07-30" @default.
• W2963208784 creator A5011672584 @default.
• W2963208784 creator A5041457930 @default.
• W2963208784 creator A5048265125 @default.
• W2963208784 date "2019-04-01" @default.
• W2963208784 modified "2023-09-24" @default.
• W2963208784 title "Dreaming neural networks: Forgetting spurious memories and reinforcing pure ones" @default.
• W2963208784 cites W1597286183 @default.
• W2963208784 cites W1970073498 @default.
• W2963208784 cites W1978076887 @default.
• W2963208784 cites W1990390131 @default.
• W2963208784 cites W1995114494 @default.
• W2963208784 cites W1996283629 @default.
• W2963208784 cites W2024060531 @default.
• W2963208784 cites W2026119411 @default.
• W2963208784 cites W2030358500 @default.
• W2963208784 cites W2030450972 @default.
• W2963208784 cites W2032558547 @default.
• W2963208784 cites W2040260270 @default.
• W2963208784 cites W2043615441 @default.
• W2963208784 cites W2044707217 @default.
• W2963208784 cites W2048087827 @default.
• W2963208784 cites W2059994748 @default.
• W2963208784 cites W2060277733 @default.
• W2963208784 cites W2069129925 @default.
• W2963208784 cites W2076327464 @default.
• W2963208784 cites W2080277460 @default.
• W2963208784 cites W2080792322 @default.
• W2963208784 cites W2090110907 @default.
• W2963208784 cites W2102656701 @default.
• W2963208784 cites W2104643304 @default.
• W2963208784 cites W2107726111 @default.
• W2963208784 cites W2124468981 @default.
• W2963208784 cites W2125150881 @default.
• W2963208784 cites W2128084896 @default.
• W2963208784 cites W2141442470 @default.
• W2963208784 cites W2142733484 @default.
• W2963208784 cites W2144079442 @default.
• W2963208784 cites W2147238273 @default.
• W2963208784 cites W2738901429 @default.
• W2963208784 cites W2883260865 @default.
• W2963208784 cites W2919115771 @default.
• W2963208784 cites W3101812839 @default.
• W2963208784 cites W2088147511 @default.
• W2963208784 cites W3147726452 @default.
• W2963208784 doi "https://doi.org/10.1016/j.neunet.2019.01.006" @default.
• W2963208784 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30735914" @default.
• W2963208784 hasPublicationYear "2019" @default.
• W2963208784 type Work @default.
• W2963208784 sameAs 2963208784 @default.
• W2963208784 citedByCount "39" @default.
• W2963208784 countsByYear W29632087842018 @default.
• W2963208784 countsByYear W29632087842019 @default.
• W2963208784 countsByYear W29632087842020 @default.
• W2963208784 countsByYear W29632087842021 @default.
• W2963208784 countsByYear W29632087842022 @default.
• W2963208784 countsByYear W29632087842023 @default.
• W2963208784 crossrefType "journal-article" @default.
• W2963208784 hasAuthorship W2963208784A5011672584 @default.
• W2963208784 hasAuthorship W2963208784A5041457930 @default.
• W2963208784 hasAuthorship W2963208784A5048265125 @default.
• W2963208784 hasBestOaLocation W29632087842 @default.
• W2963208784 hasConcept C111437709 @default.
• W2963208784 hasConcept C11413529 @default.
• W2963208784 hasConcept C119857082 @default.
• W2963208784 hasConcept C121332964 @default.
• W2963208784 hasConcept C121864883 @default.
• W2963208784 hasConcept C154945302 @default.
• W2963208784 hasConcept C2779127903 @default.
• W2963208784 hasConcept C41008148 @default.
• W2963208784 hasConcept C50644808 @default.
• W2963208784 hasConcept C53442348 @default.
• W2963208784 hasConcept C97256817 @default.
• W2963208784 hasConceptScore W2963208784C111437709 @default.
• W2963208784 hasConceptScore W2963208784C11413529 @default.
• W2963208784 hasConceptScore W2963208784C119857082 @default.
• W2963208784 hasConceptScore W2963208784C121332964 @default.
• W2963208784 hasConceptScore W2963208784C121864883 @default.
• W2963208784 hasConceptScore W2963208784C154945302 @default.
• W2963208784 hasConceptScore W2963208784C2779127903 @default.
• W2963208784 hasConceptScore W2963208784C41008148 @default.
• W2963208784 hasConceptScore W2963208784C50644808 @default.
• W2963208784 hasConceptScore W2963208784C53442348 @default.
• W2963208784 hasConceptScore W2963208784C97256817 @default.
• W2963208784 hasFunder F4320321873 @default.
• W2963208784 hasFunder F4320333369 @default.
• W2963208784 hasFunder F4320334899 @default.
• W2963208784 hasLocation W29632087841 @default.
• W2963208784 hasLocation W29632087842 @default.
• W2963208784 hasLocation W29632087843 @default.
• W2963208784 hasOpenAccess W2963208784 @default.
• W2963208784 hasPrimaryLocation W29632087841 @default.
• W2963208784 hasRelatedWork W1486099719 @default.
• W2963208784 hasRelatedWork W1618190107 @default.
• W2963208784 hasRelatedWork W1830291189 @default.
• W2963208784 hasRelatedWork W1991841905 @default.
• W2963208784 hasRelatedWork W2100553090 @default.

• next