loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Seiya Satoh 1 and Ryohei Nakano 2

Affiliations: 1 National Institute of Advanced Industrial Science and Tech, Japan ; 2 Chubu University, Japan

Keyword(s): Complex-valued Neural Networks, Complex-valued Multilayer Perceptron, Learning Method, Singular Region, Singularity Stairs Following.

Related Ontology Subjects/Areas/Topics: Artificial Intelligence ; Biomedical Engineering ; Biomedical Signal Processing ; Computational Intelligence ; Health Engineering and Technology Applications ; Human-Computer Interaction ; Learning Paradigms and Algorithms ; Methodologies and Methods ; Neural Networks ; Neurocomputing ; Neurotechnology, Electronics and Informatics ; Pattern Recognition ; Physiological Computing Systems ; Sensor Networks ; Signal Processing ; Soft Computing ; Theory and Methods

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 l earning methods. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.145.109.244

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
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 (IJCCI 2017) - IJCCI; ISBN 978-989-758-274-5; ISSN 2184-3236, SciTePress, pages 45-53. DOI: 10.5220/0006496500450053

@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 (IJCCI 2017) - IJCCI},
year={2017},
pages={45-53},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006496500450053},
isbn={978-989-758-274-5},
issn={2184-3236},
}

TY - CONF

JO - Proceedings of the 9th International Joint Conference on Computational Intelligence (IJCCI 2017) - IJCCI
TI - Performance of Complex-Valued Multilayer Perceptrons Largely Depends on Learning Methods
SN - 978-989-758-274-5
IS - 2184-3236
AU - Satoh, S.
AU - Nakano, R.
PY - 2017
SP - 45
EP - 53
DO - 10.5220/0006496500450053
PB - SciTePress