Abstract
A chaotic neural network proposed (CNN) by Aihara et al. is able to recollect stored patterns dynamically. But there are difficult cases such as its long time processing of association, and difficult to recall a specific stored pattern during the dynamical associations. We have proposed to find the optimal parameters using meta-heuristics methods to improve association performance, for example, the shorter recalling time and higher recollection rates of stored patterns in our previous works. However, the relationship between the different values of parameters of chaotic neurons and the association performance of CNN was not investigated clearly. In this paper, we propose a method to analyze the spatiotemporal changes of internal states in CNN and, by the method, analyze how the change of values of internal parameters of chaotic neurons affects the characteristics of chaotic neurons when multiple patterns are stored in the CNN. Quantile–Quantile plot, least square approximation, hierarchical clustering, and Hilbert transform are used to investigate the similarity of internal states of chaotic neurons, and to classify the neurons. Simulation results showed that how different values of an internal parameter yielded different behaviors of chaotic neurons and it suggests the optimal parameter which generates higher association performance may concern with the stored patterns of the CNN.
Similar content being viewed by others
References
Aihara K, Tanaka T, Toyoda M (1990) Chaotic neural network. Phys Lett A 144(6-7):333–340
Adachi M, Aihara K (1997) Associative dynamics in a chaotic neural network. Neural Netw 10(1):83–98
Hasegawa M, Ikeguchi T, Aihara K (2002) Solving large scale traveling salesman problems by chaotic neurondynamics. Neural Netw 15(2):271–283
Horio Y, Ando H, Aihara K (2009) Fundamental technology for complex computational systems. IEICE Fundam Rev 3(2):34–44 (in Japanese)
Horio Y (2009) Chaotic neural network system and its applications. Syst Control Inf 53(8):337–342 (in Japanese)
Obayashi M, Feng LB, Kuremoto T, Kobayashi K (2010) Intelligent agent construction using the attentive characteristic pattern of chaotic neural networks. Artif Life Robot 15:216–220
Kuremoto T, Watanabe S, Kobayashi K, Feng LB, Obayashi M (2011) Dynamical recollection of interconnected neural networks using meta-heuristics. IEEJ Trans Electron Inf Syst 131(8):1475–1484 (in Japanese)
Kuremoto T, Watanabe S, Kobayashi K, Feng LB, Obayashi M (2012) Dynamical recollection of interconnected neural networks using meta-heuristics. Electron Commun Japan 95(6):12–23
Wilk MB, Gnanadesikan R (1968) Probability plotting methods for the analysis of data. Biometrika 55(1):1–17
Johnson SC (1967) Hierarchical clustering schemes. Psychometrika 32(3):241–254
Quatiery TF, Oppenheim AV (1981) Iterative techniques for minimum phase signal reconstruction from phase or magnitude. IEEE Trans Acoust Speech Signal Process 29(6):1187–1193
Hebb DO (1949) The organization of behavior. Wiley, New York
Oseledets VI (1968) A multiplicative ergodic theorem. Characteristic Ljapunov, exponents of dynamical systems. Tr Mosk Mat Obs 19:179–210 (in Russian)
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was presented in part at the 18th International Symposium on Artificial Life and Robotics, Daejeon, Korea, January 30–February 1, 2013.
About this article
Cite this article
Watanabe, S., Kuremoto, T., Kobayashi, K. et al. A method for analyzing the spatiotemporal changes of chaotic neural networks. Artif Life Robotics 18, 196–203 (2013). https://doi.org/10.1007/s10015-013-0114-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10015-013-0114-0