The Recollection Characteristics of Generalized MCNN Using Different Control Methods
- 10.2991/jrnal.2014.1.1.14How to use a DOI?
- chaotic neural network, association memory, time-series pattern, particle swarm optimization
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.
- © 2013, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - JOUR AU - Shun Watanabe AU - Takashi Kuremoto AU - Shingo Mabu AU - Masanao Obayashi AU - Kunikazu Kobayashi PY - 2014 DA - 2014/06/30 TI - The Recollection Characteristics of Generalized MCNN Using Different Control Methods JO - Journal of Robotics, Networking and Artificial Life SP - 73 EP - 79 VL - 1 IS - 1 SN - 2352-6386 UR - https://doi.org/10.2991/jrnal.2014.1.1.14 DO - 10.2991/jrnal.2014.1.1.14 ID - Watanabe2014 ER -