Skip to main navigation Skip to search Skip to main content

A new adaptive learning algorithm using magnified gradient function

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

Abstract

In this paper, a new algorithm is proposed to solve the "flat spot" problem in back-propagation networks by magnifying the gradient function. The idea of the new learning algorithm is to vary the gradient of the activation function so as to magnify the backward propagated error signal gradient function especially when the output approaches a wrong value, thus the convergence rate can be accelerated and the flat spot problem can be eliminated. Simulation results show that, in terms of the convergence rate and global search capability, the new algorithm always outperforms the other traditional methods.
Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Pages156-159
Volume1
Publication statusPublished - 2001
Externally publishedYes
EventInternational Joint Conference on Neural Networks (IJCNN'01) - Washington, DC, United States
Duration: 15 Jul 200119 Jul 2001

Publication series

Name
Volume1

Conference

ConferenceInternational Joint Conference on Neural Networks (IJCNN'01)
PlaceUnited States
CityWashington, DC
Period15/07/0119/07/01

Fingerprint

Dive into the research topics of 'A new adaptive learning algorithm using magnified gradient function'. Together they form a unique fingerprint.

Cite this