Adaptive classification of temporal signals in fixed-weights recurrent neural networks: an existence proof

Simple item page
dc.creatorTyukin, Ivan
dc.creatorProkhorov, Danil
dc.creatorvan Leeuwen, Cees
dc.date2007-05-23
dc.date.accessioned2026-07-07T08:02:58Z
dc.date.available2026-07-07T08:02:58Z
dc.descriptionWe address the important theoretical question why a recurrent neural network with fixed weights can adaptively classify time-varied signals in the presence of additive noise and parametric perturbations. We provide a mathematical proof assuming that unknown parameters are allowed to enter the signal nonlinearly and the noise amplitude is sufficiently small.
dc.description22 pages
dc.identifierhttps://arxiv.org/abs/0705.3370
dc.identifierhttp://arxiv.org/abs/0705.3370
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/129413
dc.subjectOptimization and Control
dc.subjectDynamical Systems
dc.subject82C32; 35B40; 37C70; 68T05
dc.titleAdaptive classification of temporal signals in fixed-weights recurrent neural networks: an existence proof
dc.typetext

Files

Collections

arXiv