STORING LIMIT CYCLES USING DELAYED FEEDBACK NEURAL NETWORKS

Guikun Wu () and Hong Zhao ()
Additional contact information
Guikun Wu: Department of Physics, and Institute of Theoretical Physics and Astrophysics, Xiamen University, Xiamen 361005, China
Hong Zhao: Department of Physics, and Institute of Theoretical Physics and Astrophysics, Xiamen University, Xiamen 361005, China

Advances in Complex Systems (ACS), 2008, vol. 11, issue 03, 433-442

Abstract: We show that the delayed feedback neural networks for storing limit cycles can be trained using a global training algorithm. It is found that the storage capacity of the networks is in proportion to delay length as in the networks trained by the correlation learning based on Hebb's rule, but is much higher than in the latter. The generalization capacity of the networks is also higher than in the latter. Another interesting finding is that the spurious states or unwanted attractors totally disappear in the networks trained by the global training algorithm if the memory limit cycles are sufficiently long. The dynamics of the networks is investigated as a function of the length of limit cycles.

Keywords: Delayed feedback; neural network; global training algorithm; attractor; limit cycle (search for similar items in EconPapers)
Date: 2008
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S0219525908001738
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:acsxxx:v:11:y:2008:i:03:n:s0219525908001738

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0219525908001738

Access Statistics for this article

Advances in Complex Systems (ACS) is currently edited by Frank Schweitzer

More articles in Advances in Complex Systems (ACS) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().