Further results on controllability of recurrent neural networks

Simple item page
dc.creatorSontag, Eduardo D.
dc.creatorQiao, Y.
dc.date1999-02-03
dc.date.accessioned2026-07-07T05:27:46Z
dc.date.available2026-07-07T05:27:46Z
dc.descriptionThis paper studies controllability properties of recurrent neural networks. The new contributions are: (1) an extension of the result in the previous paper "Complete controllability of continuous-time recurrent neural networks" (Sontag and Sussmann) to a slightly different model, where inputs appear in an affine form, (2) a formulation and proof of a necessary and sufficient condition, in terms of local-local controllability, and (3) a complete analysis of the 2-dimensional case for which the hypotheses made in previous work do not apply
dc.description12 pages
dc.identifierhttps://arxiv.org/abs/math/9902023
dc.identifierhttp://arxiv.org/abs/math/9902023
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/78048
dc.subjectOptimization and Control
dc.subject93B05
dc.titleFurther results on controllability of recurrent neural networks
dc.typetext

Files

Collections

arXiv