Abstract
Chaotic neural network with external inputs has been used as a mixed input pattern separator. In contrast to previous work on the subject, highly chaotic dynamical system (LLE ≈ 0.6) is applied here. The network is based on a “dynamical mapping” scheme as an effective framework for cortical mapping. This feature allows for a more effective pattern retrieval and separation by the network.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Aihara, K., Takabe, T., Toyoda, M.: Chaotic neural networks. Physics Letters A 144, 333–340 (1990)
Adachi, M., Aihara, K.: Associative dynamics in a chaotic neural networks. Neural Networks 10, 83–98 (1997)
Adachi, M., Aihara, K., Cichocki, A.: Separation of mixed patterns by chaotic neural network. In: International Symposium on Nonlinear Theory and its Application (NOLTA), Katsurahama-so, Kochi, Japan, pp. 93–96 (1996)
Hoshino, O., Usuba, N., Kashimori, Y., Kambara, T.: Role of itinerancy as dynamical map in distributed coding scheme. Neural Networks 10, 1375–1390 (1997)
Tsuda, I.: Dynamical link of memory - chaotic memory map in nonequilibrium neural networks. Neural Networks 5, 313–326 (1992)
Nara, S., Davis, P., Toksuji, H.: Memory search using complex dynamics in reccurent neural network model. Neural Networks 6, 963–973 (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Matykiewicz, P. (2004). Chaotic Itinerancy for Patterns Separation. In: Rutkowski, L., Siekmann, J.H., Tadeusiewicz, R., Zadeh, L.A. (eds) Artificial Intelligence and Soft Computing - ICAISC 2004. ICAISC 2004. Lecture Notes in Computer Science(), vol 3070. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24844-6_31
Download citation
DOI: https://doi.org/10.1007/978-3-540-24844-6_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22123-4
Online ISBN: 978-3-540-24844-6
eBook Packages: Springer Book Archive