
For FullText PDF, please login, if you are a member of IEICE,
or go to Pay Per View on menu list, if you are a nonmember of IEICE.

Guaranteed Storing of Limit Cycles into a DiscreteTime Asynchronous Neural Network
Kenji NOWARA Toshimichi SAITO
Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Vol.E75A
No.11
pp.15791582 Publication Date: 1992/11/25
Online ISSN:
DOI:
Print ISSN: 09168508 Type of Manuscript: PAPER Category: Neural Networks Keyword: neural network, associative memory, limit cycles, correlation matrix,
Full Text: PDF(281.8KB)>>
Summary:
This article discusses a synthesis procedure of a discretetime asynchronous neural network whose information is a limit cycle. The synthesis procedure uses a novel connection matrix and can be reduced into a linear epuation. If all elements of desired limit cycles are independent at each transition step, the equation can be solved and all desired limit cycles can be stored. In some experiments, our procedure exhibits much better storing performance than previous ones.

