Subset based training and pruning of sigmoid neural networks

Guian Zhou, Jennie Si

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

Abstract

In the present paper we develop two algorithms, Subset Based Training (SBT) and Subset Based Training and Pruning (SBTP), using the fact that the Jacobian matrices in sigmoid network training problems are usually rank deficient. The weight vectors are divided into two parts during training, according to the Jacobian rank sizes. Both SBT and SBTP are trust region methods. Comparing to the standard Levenberg-Marquardt (LM) method, these two algorithms can achieve similar convergence properties as the LM but with less memory requirements. Furthermore the SBTP combines training and pruning of a network into one comprehensive procedure. Some convergence properties of the two algorithms are given to qualitatively evaluate the performance of the algorithms.

Original languageEnglish (US)
Title of host publicationProceedings of the 1998 American Control Conference, ACC 1998
Pages58-62
Number of pages5
DOIs
StatePublished - Dec 1 1998
Event1998 American Control Conference, ACC 1998 - Philadelphia, PA, United States
Duration: Jun 24 1998Jun 26 1998

Publication series

NameProceedings of the American Control Conference
Volume1
ISSN (Print)0743-1619

Other

Other1998 American Control Conference, ACC 1998
CountryUnited States
CityPhiladelphia, PA
Period6/24/986/26/98

    Fingerprint

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Zhou, G., & Si, J. (1998). Subset based training and pruning of sigmoid neural networks. In Proceedings of the 1998 American Control Conference, ACC 1998 (pp. 58-62). [694628] (Proceedings of the American Control Conference; Vol. 1). https://doi.org/10.1109/ACC.1998.694628