Local-step Optimization in Online Update Learning of Multilayer Perceptrons

다충신경망을 위한 온라인방식 학습의 개별학습단계 최적화 방법

  • Published : 2004.10.01

Abstract

A local-step optimization method is proposed to supplement the global-step optimization methods which adopt online update mode of internal weights and error energy as stop criterion in learning of multilayer perceptrons (MLPs). This optimization method is applied to the standard online error backpropagation(EBP) and the performance is evaluated for a speaker verification system.

Keywords