A new terminating condition to identify the convergence of the learning process in multi-layer feed-forward neural networks

Sean Shensheng Xu, Chi Chung Cheung

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

Multi-layer feed-forward neural networks are commonly used in supervised learning, for which data training is required. One popular way to check whether the training is completed is to monitor the mean square error. It is expected that the learning is completed when the mean square error is less than or equal to an error threshold, which is usually a very small positive real number (e.g., 0.001). However, this terminating condition does not always work very effectively. This paper proposes a new terminating condition to identify the convergence of the learning process in multi-layer feed-forward neural networks. The new termination condition is called Threshold of Output Differences (TOD), which is the difference between an ouput value and its corresponding desired (target) output value to identify the convergence of the learning process. It proposes that the learning is completed when the difference for each output is less than a threshold. The performance investigation showed that the convergence rate of a learning algorithm with this new terminating condition is generally faster than the original one. Moreover, the classification rate (generalization) of a learning algorithm with TOD is usually better than the original one.

Original languageEnglish
Title of host publication2015 International Joint Conference on Neural Networks, IJCNN 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781479919604, 9781479919604, 9781479919604, 9781479919604
DOIs
Publication statusPublished - 12 Jul 2015
EventInternational Joint Conference on Neural Networks, IJCNN 2015 - Killarney, Ireland
Duration: 12 Jul 201517 Jul 2015

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume2015-September

Conference

ConferenceInternational Joint Conference on Neural Networks, IJCNN 2015
CountryIreland
CityKillarney
Period12/07/1517/07/15

Keywords

  • Breast
  • Cancer
  • Iris

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this