A simple procedure in back-propagation training

Chien Cheng Yu, Bin-Da Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

The standard back-propagation (BP) algorithm for multilayer feedforward neural networks is basically a gradient-descent method, it has the problems of local minima and slow convergence. In this paper, a simple method based on the BP algorithm by employing an adaptive learning rate and momentum factor to reduce the training time is presented. Simulation results indicate a superior convergence speed as compared to other competing methods.

Original languageEnglish
Title of host publication2001 International Conferences on Info-Tech and Info-Net
Subtitle of host publicationA Key to Better Life, ICII 2001 - Proceedings
EditorsZhongzhi Shi, Hui Li, Y.X. Zhong
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages529-535
Number of pages7
ISBN (Electronic)0780370104, 9780780370104
DOIs
Publication statusPublished - 2001 Jan 1
EventInternational Conferences on Info-Tech and Info-Net, ICII 2001 - Beijing, China
Duration: 2001 Oct 292001 Nov 1

Publication series

Name2001 International Conferences on Info-Tech and Info-Net: A Key to Better Life, ICII 2001 - Proceedings
Volume3

Other

OtherInternational Conferences on Info-Tech and Info-Net, ICII 2001
CountryChina
CityBeijing
Period01-10-2901-11-01

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Signal Processing
  • Computers in Earth Sciences
  • Control and Systems Engineering
  • Instrumentation

Fingerprint Dive into the research topics of 'A simple procedure in back-propagation training'. Together they form a unique fingerprint.

Cite this