Solving Time of Least Square Systems in Sigma-Pi Unit Networks

Simple item page
dc.creatorCourrieu, Pierre
dc.date2008-04-30
dc.date.accessioned2026-07-07T12:18:32Z
dc.date.available2026-07-07T12:18:32Z
dc.descriptionThe solving of least square systems is a useful operation in neurocomputational modeling of learning, pattern matching, and pattern recognition. In these last two cases, the solution must be obtained on-line, thus the time required to solve a system in a plausible neural architecture is critical. This paper presents a recurrent network of Sigma-Pi neurons, whose solving time increases at most like the logarithm of the system size, and of its condition number, which provides plausible computation times for biological systems.
dc.descriptionNombre de pages: 7
dc.identifierhttps://arxiv.org/abs/0804.4808
dc.identifierhttp://arxiv.org/abs/0804.4808
dc.identifierNeural Information Processing - Letters and Reviews 4, 3 (2004) 39-45
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/212441
dc.subjectNeural and Evolutionary Computing
dc.titleSolving Time of Least Square Systems in Sigma-Pi Unit Networks
dc.typetext

Files

Collections

arXiv