Self-consistent signal-to-noise analysis and its application to analogue neural networks with asymmetric connections

DOI10.1088/0305-4470/25/7/017zbMath0800.68685OpenAlexW2046995962MaRDI QIDQ4019059

Masatoshi Shiino, Tomoki Fukai

Publication date: 16 January 1993

Published in: Journal of Physics A: Mathematical and General (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1088/0305-4470/25/7/017

zbMATH Keywords

neural networkslearningstorage capacityneuronssignal-to-noise analysisinput-output relationsIsing spin type neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) Information storage and retrieval of data (68P20)

Related Items (10)

Associative memory by recurrent neural networks with delay elements ⋮ Mixed states on neural network with structural learning ⋮ Localized activity profiles and storage capacity of rate-based autoassociative networks ⋮ Hierarchical neural networks perform both serial and parallel processing ⋮ How well do mean field theories of spiking quadratic-integrate-and-fire networks work in realistic parameter regimes? ⋮ Topological pattern selection in recurrent networks ⋮ Statistical mechanics approach to 1-bit compressed sensing ⋮ Bayesian signal reconstruction for 1-bit compressed sensing ⋮ Approximate message passing for nonconvex sparse regularization with stability and asymptotic analysis ⋮ Notions of associative memory and sparse coding

This page was built for publication: Self-consistent signal-to-noise analysis and its application to analogue neural networks with asymmetric connections