Backpropagation Convergence Via Deterministic Nonmonotone Perturbed Minimization

dc.contributor.author	Solodov, Mikhail
dc.contributor.author	Mangasarian, Olvi
dc.date.accessioned	2013-01-25T19:44:22Z
dc.date.available	2013-01-25T19:44:22Z
dc.date.issued	1994
dc.identifier.citation	94-06	en
dc.identifier.uri	http://digital.library.wisc.edu/1793/64530
dc.description.abstract	The fundamental backpropagation (BP) algorithm for training artificial neural networks is cast as a deterministic nonmonotone perturbed gradient method. Under certain natural assumptions, such as the series of learning rates diverging while the series of their squares converging, it is established that every accumulation point of the online BP iterates is a stationary point of the BP error function. The result presented cover serial and parallel online BP, modified BP with a momentum term, and BP with weight decay	en
dc.subject	backpropagation convergence	en
dc.title	Backpropagation Convergence Via Deterministic Nonmonotone Perturbed Minimization	en
dc.type	Technical Report	en

Math Prog Technical Reports
Math Prog Technical Reports Archive for the Department of Computer Sciences at the University of Wisconsin-Madison