Faster RBF Network Learning Utilizing Singular Regions

Seiya Satoh, Ryohei Nakano

2019

Abstract

There are two ways to learn radial basis function (RBF) networks: one-stage and two-stage learnings. Recently a very powerful one-stage learning method called RBF-SSF has been proposed, which can stably find a series of excellent solutions, making good use of singular regions, and can monotonically decrease training error along with the increase of hidden units. RBF-SSF was built by applying the SSF (singularity stairs following) paradigm to RBF networks; the SSF paradigm was originally and successfully proposed for multilayer perceptrons. Although RBF-SSF has the strong capability to find excellent solutions, it required a lot of time mainly because it computes the Hessian. This paper proposes a faster version of RBF-SSF called RBF-SSF(pH) by introducing partial calculation of the Hessian. The experiments using two datasets showed RBF-SSF(pH) ran as fast as usual one-stage learning methods while keeping the excellent solution quality.

Paper Citation

in Harvard Style

Satoh S. and Nakano R. (2019). Faster RBF Network Learning Utilizing Singular Regions.In Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-351-3, pages 501-508. DOI: 10.5220/0007367205010508

in Bibtex Style

@conference{icpram19,
author={Seiya Satoh and Ryohei Nakano},
title={Faster RBF Network Learning Utilizing Singular Regions},
booktitle={Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2019},
pages={501-508},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007367205010508},
isbn={978-989-758-351-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Faster RBF Network Learning Utilizing Singular Regions
SN - 978-989-758-351-3
AU - Satoh S.
AU - Nakano R.
PY - 2019
SP - 501
EP - 508
DO - 10.5220/0007367205010508