Abstract
The role of chaotic behavior in neural network model has been studied by several researchers. We bring forward an evidence that the chaotic neural network modules can be integrated without controller. In our two-body neural network model, the chaotic behavior plays the role of a mechanism that integrates network modules. Integration of modules was realized by timeshared pattern recalling. This result provides another viewpoint of chaos in neural network model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Y. Yao and W.J. Freeman. Model of biological pattern recognition with spatially chaotic dynamics, Neural Networks, Vol.3, pp.153–170, 1990.
I. Tsuda. Dynamic link of memory — chaotic memory map in nonequilibrium neural networks, Neural Networks, Vol.5, pp.313–326, 1992.
M. Adachi, K. Aihara, and M. Kotani. Nonlinear Associative Dynamics in A Chaotic Neural Network, In Proc. of the 2nd International Conference on Fuzzy Logic & Neural Networks, pp.947–950, 1992.
S. Nara, P. Davis, and H. Totsuji. Memory search using complex dynamics in a recurrent neural network model. Neural Networks, Vol.6, pp.963, 1993.
B.L.M. Happel and J.M.J. Murre. Evolving complex dynamics in modular interactive neural networks, 1996, (preprint).
A. Sano. The role of intersubsystem coupling density and chaotic dynamics in multi-body neural network model, In Proc. of the IIW95, TR-95010 of RWC Technical Report, pp.41–53, RWCP, 1995.
H. Nozawa. A Neural Network Model as a Globally Coupled Map and Applications Based on Chaos, Chaos, Vol.2, pp.377–386, 1992.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1997 Springer-Verlag Tokyo
About this paper
Cite this paper
Sano, A. (1997). Pattern Recalling Property of Neural Network Modules Integrated by Chaos. In: Nakamura, E.R., Kudo, K., Yamakawa, O., Tamagawa, Y. (eds) Complexity and Diversity. Springer, Tokyo. https://doi.org/10.1007/978-4-431-66862-6_6
Download citation
DOI: https://doi.org/10.1007/978-4-431-66862-6_6
Publisher Name: Springer, Tokyo
Print ISBN: 978-4-431-66864-0
Online ISBN: 978-4-431-66862-6
eBook Packages: Springer Book Archive