The Recollection Characteristics of Generalized MCNN Using Different Control Methods

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.2014.1.1.14How to use a DOI?
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/).