A fast learning algorithm with promising convergence capability

Chi Chung Cheung, Sin Chun Ng, Andrew K. Lui, Sean Shensheng Xu

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

7 Citations (Scopus)


Backpropagation (BP) learning algorithm is the most widely supervised learning technique which is extensively applied in the training of multi-layer feed-forward neural networks. Many modifications of BP have been proposed to speed up the learning of the original BP. However, these modifications sometimes cannot converge properly due to the local minimum problem. This paper proposes a new algorithm, which provides a systematic approach to make use of the characteristics of different fast learning algorithms so that the convergence of a learning process is promising with a fast learning rate. Our performance investigation shows that the proposed algorithm always converges with a fast learning rate in two popular complicated applications whereas other popular fast learning algorithms give very poor global convergence capabilities in these two applications.

Original languageEnglish
Title of host publication2011 International Joint Conference on Neural Networks, IJCNN 2011 - Final Program
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Print)9781457710865
Publication statusPublished - 31 Jul 2011
Event2011 International Joint Conference on Neural Network, IJCNN 2011 - San Jose, CA, United States
Duration: 31 Jul 20115 Aug 2011

Publication series

NameProceedings of the International Joint Conference on Neural Networks


Conference2011 International Joint Conference on Neural Network, IJCNN 2011
Country/TerritoryUnited States
CitySan Jose, CA

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this