Toward a new three layer neural network with dynamical optimal training performance

Chi-Hsu Wang*, Shu Fan Lin

*Corresponding author for this work

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

2 Scopus citations

Abstract

This paper proposes a revised dynamic optimal training algorithm for a three layer neural network with sigmoid activation function in the hidden layer and linear activation function in the output layer. This three layer neural network can be used for classification problems, such as the classification of Iris data. This revised dynamic optimal training finds optimal learning rate with its upper-bound for next iteration to guarantee optimal convergence of training result. With modification of initial weighting factors and activation functions, revised dynamic optimal training algorithm is more stable and faster than dynamic optimal training algorithm. Excellent improvements of computing time and robustness have been obtained for Iris data set.

Original languageEnglish
Title of host publication2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007
Pages3101-3106
Number of pages6
DOIs
StatePublished - 1 Dec 2007
Event2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007 - Montreal, QC, Canada
Duration: 7 Oct 200710 Oct 2007

Publication series

NameConference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
ISSN (Print)1062-922X

Conference

Conference2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007
CountryCanada
CityMontreal, QC
Period7/10/0710/10/07

Keywords

  • Iris data
  • Neural network
  • Optimal training

Fingerprint Dive into the research topics of 'Toward a new three layer neural network with dynamical optimal training performance'. Together they form a unique fingerprint.

  • Cite this

    Wang, C-H., & Lin, S. F. (2007). Toward a new three layer neural network with dynamical optimal training performance. In 2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007 (pp. 3101-3106). [4414207] (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics). https://doi.org/10.1109/ICSMC.2007.4414207