Abstract
A stimulus-response scheme is introduced in chaotic neural networks with synaptic plasticities and the processes of dynamic learning under external stimuli are investigated. Owing to the refractoriness and the time-hysteresis, memory fixing abilities of stimuli become much higher than those by the Hopfield neural network with/without stochastic activities and also have sensitive dependences on the strength of stimulation. These characteristics turn out to be supported with the chaotic activity by examining the relation between the refractoriness and the Lyapunov exponent during the engraving of stimuli on the network. The above results indicate a possibility of realizing the real-time learning mechanism against the external time series inputs, which is difficult for the static Hopfield model of associative memory. Furthermore, modeling of dynamic retrieval mechanism is attempted for diverse switching phenomena on the chaotic neural network with grown (fixed) synapses.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
K. Aihara, T. Takabe, M. Toyoda, Chaotic Neural Networks, Physics Letters, A144, 1990, pp.333–340.
H. Nishimura, Y. Fujita, S. Fujita, A Mechanism for Dynamic Association Based on Chaotic Neural Networks, Proc. of 1994 Annual Conf. of JNNS, 1994, pp.104–105 (in Japanese).
H. Nishimura, N. Katada, Dynamic Learning Processes in Chaotic Neural Networks, Proc. of 1995 Annual Conf of JNNS, 1995, pp.117–118 (in Japanese).
M. Adachi, K. Aihara, An analysis of associatve transient dynamics in a chaotic neural network, inTowards the Harnessing of Chaos, Elsevier, 1994, pp.335–338.
B. Müller, J. Reinhardt, Neural Networks: An Introduction, Springer-Verlag, 1990.
K. Kaneko, Clustering, coding, switching, hierarchical ordering, and control in a network of chaotic elements, Physica D41, 1990, pp.137–172.
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
Nishimura, H., Katada, N., Fujita, Y. (1997). Dynamic Learning and Retrieving Scheme Based on Chaotic Neuron Model. 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_10
Download citation
DOI: https://doi.org/10.1007/978-4-431-66862-6_10
Publisher Name: Springer, Tokyo
Print ISBN: 978-4-431-66864-0
Online ISBN: 978-4-431-66862-6
eBook Packages: Springer Book Archive