articleTop 1% cited
The Enhanced Storage Capacity in Neural Networks with Low Activity Level
Europhysics Letters (EPL) · 1988 · Vol. 6(2) · pp. 101–105
Misha Tsodyks✉(Russian Academy of Sciences)M. V. Feigel’man(Landau Institute for Theoretical Physics)
Abstract
The modified Hopfield model defined in terms of "V-variables" (V = 0; 1), which is appropriate for storage of correlated patterns, is considered. The learning algorithm is proposed to enhance significantly the storage capacity in comparison with previous estimates. At low levels of neural activity, p ≪ 1, we obtain αc(p) ∼ (p|ln p|)-1 which resembles Gardner's estimate for the maximum storage capacity.
Neural Networks and ApplicationsModel Reduction and Neural NetworksImage and Signal Denoising MethodsArtificial neural networkComputer scienceStorage modelComputer data storageBiological systemMaterials scienceArtificial intelligenceBiologyComputer hardware
Citations
468
FWCI
24.33
field-weighted impact
References
13
Percentile
100%
vs. same field & year
Citations per year
Cited by
Model of global spontaneous activity and local structured activity during delay periods in the cerebral cortex
Cerebral Cortex · 1997 · 1,134 citations
References
Statistical mechanics of neural networks near saturation
Annals of Physics · 1987 · 855 citations
Spin-glass models of neural networks
Physical review. A, General physics · 1985 · 1,204 citations
Neural networks and physical systems with emergent collective computational abilities.
Proceedings of the National Academy of Sciences · 1982 · 19,120 citations
Citation Network
How this paper connects to the literature. Drag to explore, click any node to open that paper.