Hits:

Indexed by:期刊论文

Date of Publication:2009-06-01

Journal:NEURAL PROCESSING LETTERS

Included Journals:SCIE、EI、Scopus

Volume:29

Issue:3

Page Number:205-212

ISSN No.:1370-4621

Key Words:Feedforward neural networks; Linear output; Online gradient method; Penalty; Boundedness; Convergence

Abstract:This paper investigates an online gradient method with penalty for training feedforward neural networks with linear output. A usual penalty is considered, which is a term proportional to the norm of the weights. The main contribution of this paper is to theoretically prove the boundedness of the weights in the network training process. This boundedness is then used to prove an almost sure convergence of the algorithm to the zero set of the gradient of the error function.