A Global Algorithm for Training Multilayer Neural Networks

Simple item page
dc.creatorZhao, Hong
dc.creatorJin, Tao
dc.date2006-07-06
dc.date.accessioned2026-07-07T07:22:34Z
dc.date.available2026-07-07T07:22:34Z
dc.descriptionWe present a global algorithm for training multilayer neural networks in this Letter. The algorithm is focused on controlling the local fields of neurons induced by the input of samples by random adaptations of the synaptic weights. Unlike the backpropagation algorithm, the networks may have discrete-state weights, and may apply either differentiable or nondifferentiable neural transfer functions. A two-layer network is trained as an example to separate a linearly inseparable set of samples into two categories, and its powerful generalization capacity is emphasized. The extension to more general cases is straightforward.
dc.identifierhttps://arxiv.org/abs/physics/0607046
dc.identifierhttp://arxiv.org/abs/physics/0607046
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/115707
dc.subjectBiological Physics
dc.subjectComputational Physics
dc.titleA Global Algorithm for Training Multilayer Neural Networks
dc.typetext

Files

Collections

arXiv