Dynamic optimal training of a three layer neural network with sigmoid function

Chi-Hsu Wang*, Yu Yi Chi

*Corresponding author for this work

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

1 Scopus citations

Abstract

This paper proposes a dynamical optimal training algorithm for a three layer neural network (NN) with sigmoid activation functions in the hidden and output layers. This three layer neural network can be used for classification problems, such as the classification of Iris data. The mathematical formulation of this three layer NN is rigorously derived first in this paper, so that the dynamical optimal training of it can be performed. The dynamical optimal training process for this three layer NN is therefore presented which guarantees the convergence of the training in a minimum number of epochs. This dynamical optimal training does not use fixed learning rate for training. Instead, the learning rates are updated for next iteration to guarantee the optimal convergence of the training result. Excellent results have been obtained for XOR and Iris data set.

Original languageEnglish
Title of host publicationProceedings of the 2006 IEEE International Conference on Networking, Sensing and Control, ICNSC'06
Pages392-397
Number of pages6
DOIs
StatePublished - 1 Dec 2006
Event2006 IEEE International Conference on Networking, Sensing and Control, ICNSC'06 - Ft. Lauderdale, FL, United States
Duration: 23 Apr 200625 Apr 2006

Publication series

NameProceedings of the 2006 IEEE International Conference on Networking, Sensing and Control, ICNSC'06

Conference

Conference2006 IEEE International Conference on Networking, Sensing and Control, ICNSC'06
CountryUnited States
CityFt. Lauderdale, FL
Period23/04/0625/04/06

Fingerprint Dive into the research topics of 'Dynamic optimal training of a three layer neural network with sigmoid function'. Together they form a unique fingerprint.

  • Cite this

    Wang, C-H., & Chi, Y. Y. (2006). Dynamic optimal training of a three layer neural network with sigmoid function. In Proceedings of the 2006 IEEE International Conference on Networking, Sensing and Control, ICNSC'06 (pp. 392-397). [1673178] (Proceedings of the 2006 IEEE International Conference on Networking, Sensing and Control, ICNSC'06). https://doi.org/10.1109/ICNSC.2006.1673178