Performance of Complex-Valued Multilayer Perceptrons Largely Depends on Learning Methods

Seiya Satoh, Ryohei Nakano

2017

Abstract

Complex-valued multilayer perceptrons (C-MLPs) can naturally treat complex numbers, and therefore can work well for the processing of signals such as radio waves and sound waves, which are naturally expressed as complex numbers. The performance of C-MLPs can be measured by solution quality and processing time. We believe the performance seriously depends on which learning methods we employ since in the search space there exist many local minima and singular regions, which prevent learning methods from finding excellent solutions. Complex-valued backpropagation (C-BP) and complex-valued BFGS method (C-BFGS) are well-known for learning C-MLPs. Moreover, complex-valued singularity stairs following (C-SSF) has recently been proposed as a new learning method, which achieves successive learning by utilizing singular regions and guarantees monotonic decrease of training errors. Through experiments using five datasets, this paper evaluates how the performance of C-MLPs changes depending on learning methods.

Paper Citation

in Harvard Style

Satoh S. and Nakano R. (2017). Performance of Complex-Valued Multilayer Perceptrons Largely Depends on Learning Methods.In Proceedings of the 9th International Joint Conference on Computational Intelligence - Volume 1: IJCCI, ISBN 978-989-758-274-5, pages 45-53. DOI: 10.5220/0006496500450053

in Bibtex Style

@conference{ijcci17,
author={Seiya Satoh and Ryohei Nakano},
title={Performance of Complex-Valued Multilayer Perceptrons Largely Depends on Learning Methods},
booktitle={Proceedings of the 9th International Joint Conference on Computational Intelligence - Volume 1: IJCCI,},
year={2017},
pages={45-53},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006496500450053},
isbn={978-989-758-274-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Joint Conference on Computational Intelligence - Volume 1: IJCCI,
TI - Performance of Complex-Valued Multilayer Perceptrons Largely Depends on Learning Methods
SN - 978-989-758-274-5
AU - Satoh S.
AU - Nakano R.
PY - 2017
SP - 45
EP - 53
DO - 10.5220/0006496500450053