Matches in SemOpenAlex for { <https://semopenalex.org/work/W2043014754> ?p ?o ?g. }
- W2043014754 endingPage "67" @default.
- W2043014754 startingPage "30" @default.
- W2043014754 abstract "The Hopfield model of a neural network is studied near its saturation, i.e., when the number p of stored patterns increases with the size of the network N, as p = αN. The mean-field theory for this system is described in detail. The system possesses, at low α, both a spin-glass phase and 2p dynamically stable degenerate ferromagnetic phases. The latter have essentially full macroscopic overlaps with the memorized patterns, and provide effective associative memory, despite the spin-glass features. The network can retrieve patterns, at T = 0, with an error of less than 1.5% for α <αc = 0.14. At αc the ferromagnetic (FM) retrieval states disappear discontinuously. Numerical simulations show that even above αc the overlaps with the sored patterns are not zero, but the level of error precludes meaningful retrieval. The difference between the statistical mechanics and the simulations is discussed. As α decreases below 0.05 the FM retrieval states become ground states of the system, and for α < 0.03 mixture states appear. The level of storage creates noise, akin to temperature at finite p. Replica symmetry breaking is found to be salient in the spin-glass state, but in the retrieval states it appears at extremely low temperatures, and is argued to have a very weak effect. This is corroborated by simulations. The study is extended to survey the phase diagram of the system in the presence of stochastic synaptic noise (temperature), and the effect of external fields (neuronal thresholds) coupled to groups of patterns. It is found that a field coupled to many patterns has a very limited utility in enhancing their learning. Finally, we discuss the robustness of the network to the relaxation of various underlying assumptions, as well as some new trends in the study of neural networks." @default.
- W2043014754 created "2016-06-24" @default.
- W2043014754 creator A5023872429 @default.
- W2043014754 creator A5073266403 @default.
- W2043014754 creator A5090967567 @default.
- W2043014754 date "1987-01-01" @default.
- W2043014754 modified "2023-10-11" @default.
- W2043014754 title "Statistical mechanics of neural networks near saturation" @default.
- W2043014754 cites W1967084746 @default.
- W2043014754 cites W1987504167 @default.
- W2043014754 cites W1991904924 @default.
- W2043014754 cites W1995114494 @default.
- W2043014754 cites W1995341919 @default.
- W2043014754 cites W1997873659 @default.
- W2043014754 cites W2009110324 @default.
- W2043014754 cites W2022494241 @default.
- W2043014754 cites W2026846516 @default.
- W2043014754 cites W2040213906 @default.
- W2043014754 cites W2047900759 @default.
- W2043014754 cites W2059994748 @default.
- W2043014754 cites W2069129925 @default.
- W2043014754 cites W2080792322 @default.
- W2043014754 cites W2081261782 @default.
- W2043014754 cites W2088431067 @default.
- W2043014754 cites W2094498958 @default.
- W2043014754 cites W4241400578 @default.
- W2043014754 doi "https://doi.org/10.1016/0003-4916(87)90092-3" @default.
- W2043014754 hasPublicationYear "1987" @default.
- W2043014754 type Work @default.
- W2043014754 sameAs 2043014754 @default.
- W2043014754 citedByCount "744" @default.
- W2043014754 countsByYear W20430147542012 @default.
- W2043014754 countsByYear W20430147542013 @default.
- W2043014754 countsByYear W20430147542014 @default.
- W2043014754 countsByYear W20430147542015 @default.
- W2043014754 countsByYear W20430147542016 @default.
- W2043014754 countsByYear W20430147542017 @default.
- W2043014754 countsByYear W20430147542018 @default.
- W2043014754 countsByYear W20430147542019 @default.
- W2043014754 countsByYear W20430147542020 @default.
- W2043014754 countsByYear W20430147542021 @default.
- W2043014754 countsByYear W20430147542022 @default.
- W2043014754 countsByYear W20430147542023 @default.
- W2043014754 crossrefType "journal-article" @default.
- W2043014754 hasAuthorship W2043014754A5023872429 @default.
- W2043014754 hasAuthorship W2043014754A5073266403 @default.
- W2043014754 hasAuthorship W2043014754A5090967567 @default.
- W2043014754 hasConcept C114614502 @default.
- W2043014754 hasConcept C121332964 @default.
- W2043014754 hasConcept C121864883 @default.
- W2043014754 hasConcept C142362112 @default.
- W2043014754 hasConcept C150775274 @default.
- W2043014754 hasConcept C153349607 @default.
- W2043014754 hasConcept C154945302 @default.
- W2043014754 hasConcept C202213908 @default.
- W2043014754 hasConcept C204795200 @default.
- W2043014754 hasConcept C26873012 @default.
- W2043014754 hasConcept C2775937380 @default.
- W2043014754 hasConcept C33923547 @default.
- W2043014754 hasConcept C41008148 @default.
- W2043014754 hasConcept C44280652 @default.
- W2043014754 hasConcept C50644808 @default.
- W2043014754 hasConcept C62520636 @default.
- W2043014754 hasConcept C69523127 @default.
- W2043014754 hasConcept C72319582 @default.
- W2043014754 hasConcept C85906118 @default.
- W2043014754 hasConcept C9930424 @default.
- W2043014754 hasConcept C99874945 @default.
- W2043014754 hasConceptScore W2043014754C114614502 @default.
- W2043014754 hasConceptScore W2043014754C121332964 @default.
- W2043014754 hasConceptScore W2043014754C121864883 @default.
- W2043014754 hasConceptScore W2043014754C142362112 @default.
- W2043014754 hasConceptScore W2043014754C150775274 @default.
- W2043014754 hasConceptScore W2043014754C153349607 @default.
- W2043014754 hasConceptScore W2043014754C154945302 @default.
- W2043014754 hasConceptScore W2043014754C202213908 @default.
- W2043014754 hasConceptScore W2043014754C204795200 @default.
- W2043014754 hasConceptScore W2043014754C26873012 @default.
- W2043014754 hasConceptScore W2043014754C2775937380 @default.
- W2043014754 hasConceptScore W2043014754C33923547 @default.
- W2043014754 hasConceptScore W2043014754C41008148 @default.
- W2043014754 hasConceptScore W2043014754C44280652 @default.
- W2043014754 hasConceptScore W2043014754C50644808 @default.
- W2043014754 hasConceptScore W2043014754C62520636 @default.
- W2043014754 hasConceptScore W2043014754C69523127 @default.
- W2043014754 hasConceptScore W2043014754C72319582 @default.
- W2043014754 hasConceptScore W2043014754C85906118 @default.
- W2043014754 hasConceptScore W2043014754C9930424 @default.
- W2043014754 hasConceptScore W2043014754C99874945 @default.
- W2043014754 hasIssue "1" @default.
- W2043014754 hasLocation W20430147541 @default.
- W2043014754 hasOpenAccess W2043014754 @default.
- W2043014754 hasPrimaryLocation W20430147541 @default.
- W2043014754 hasRelatedWork W1521417684 @default.
- W2043014754 hasRelatedWork W1771600099 @default.
- W2043014754 hasRelatedWork W1966298965 @default.
- W2043014754 hasRelatedWork W1993971247 @default.
- W2043014754 hasRelatedWork W1999512041 @default.