The Recollection Characteristics of Generalized MCNN Using Different Control Methods
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...
Main Authors: | Shun Watanabe, Takashi Kuremoto, Shingo Mabu, Masanao Obayashi, Kunikazu Kobayashi |
---|---|
Format: | Article |
Language: | English |
Published: |
Atlantis Press
2014-06-01
|
Series: | Journal of Robotics, Networking and Artificial Life (JRNAL) |
Subjects: | |
Online Access: | https://www.atlantis-press.com/article/13187.pdf |
Similar Items
-
Unsupervised Image Classification Using Multi-Autoencoder and K-means++
by: Shingo Mabu, et al.
Published: (2018-06-01) -
Enhancing EEG Signals Recognition Using ROC Curve
by: Takashi Kuremoto, et al.
Published: (2018-03-01) -
Forecasting Real Time Series Data using Deep Belief Net and Reinforcement Learning
by: Takaomi Hirata, et al.
Published: (2018-03-01) -
An Improved Reinforcement Learning System Using Affective Factors
by: Takashi Kuremoto, et al.
Published: (2013-07-01) -
One-D-R-A-G-SOM and its Application to a Hand Shape Instruction Learning System
by: Takashi Kuremoto, et al.
Published: (2014-08-01)