An Improved Bound on the VC-Dimension of Neural Networks with Polynomial Activation Functions

Simple item page
dc.creatorRojas, J. Maurice
dc.creatorVidyasagar, M.
dc.date2001-12-19
dc.date2002-02-01
dc.date.accessioned2026-07-07T04:45:22Z
dc.date.available2026-07-07T04:45:22Z
dc.descriptionIn this note, we derive an improved upper bound for the VC-dimension of neural networks with polynomial activation functions. This improved bound is based on a result of Rojas on the number of connected components of a semi-algebraic set.
dc.description9 pages, submitted for publication. Various typos fixed and the proof of the main result has been streamlined
dc.identifierhttps://arxiv.org/abs/math/0112208
dc.identifierhttp://arxiv.org/abs/math/0112208
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/62927
dc.subjectOptimization and Control
dc.subjectAlgebraic Geometry
dc.titleAn Improved Bound on the VC-Dimension of Neural Networks with Polynomial Activation Functions
dc.typetext

Files

Collections

arXiv