Authors
Shun Watanabe, Takashi Kuremoto, Shingo Mabu, Masanao Obayashi, Kunikazu
Kobayashi
Corresponding Author
Takashi Kuremoto
Available Online 30 June 2014.
DOI
https://doi.org/10.2991/jrnal.2014.1.1.14
Keywords
chaotic neural network, association memory, time-series pattern, particle
swarm optimization
Abstract
Kuremoto et al. proposed a multi-layer chaotic neural network (MCNN) combined
multiple Adachi et al.'s CNNs to realize mutual auto-association of plural
time series patterns. However, the MCNN was limited in a two-layer model.
In this paper, we extend the MCNN to be a general form (GMCNN) with more
layers and use particle swarm optimization (PSO) to improve the recollection
performance of GMCNN. The recollecting characteristics by different parameter-control
methods were investigated by computer simulations.
Copyright
© 2013, the Authors. Published by ALife Robotics Corp. Ltd..
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).