ACL–adaptive correction of learning parameters for backpropagation based algorithms

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearch

Authors

We present an improvement of backpropagation learning (BP) for Sigma-Pi networks with adaptive correction of the learning parameters (ACL). An improvement of convergency is achieved by using the information value, change of the output error and the validity of Funahashi's theorem to analytically determine values for the learning parameters momentum, learning rate and learning motivation in each learning step. Its application to a neural-network based approximation of continuous input-output mappings with high accuracy yields very good results: the number of training periods of ACL BP learning is smaller than the corresponding number of training periods using other BP based learning rules.
Original languageEnglish
Title of host publicationIJCNN '99, International Joint Conference on Neural Networks : Washington, DC, July 10 - 16, 1999, Proceedings
Number of pages4
Place of PublicationPiscataway
PublisherIEEE - Institute of Electrical and Electronics Engineers Inc.
Publication date07.1999
Pages1749-1752
ISBN (print)0-7803-5529-6 , 0-7803-5530-X
DOIs
Publication statusPublished - 07.1999
EventInternational Joint Conference on Neural Networks - 1999 - Washington, DC, United States
Duration: 10.07.199916.07.1999
https://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6674