![](/images/graphics-bg.png)
Further Stability Criterion on Delayed Recurrent Neural Networks Based on Reciprocal Convex Technique
Joint Authors
Zhang, Guobao
Li, Tao
Fei, Shumin
Source
Mathematical Problems in Engineering
Issue
Vol. 2012, Issue 2012 (31 Dec. 2012), pp.1-14, 14 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2011-09-26
Country of Publication
Egypt
No. of Pages
14
Main Subjects
Abstract EN
Together with Lyapunov-Krasovskii functional theory and reciprocal convex technique, a new sufficient condition is derived to guarantee the global stability for recurrent neural networks with both time-varying and continuously distributed delays, in which one improved delay-partitioning technique is employed.
The LMI-based criterion heavily depends on both the upper and lower bounds on state delay and its derivative, which is different from the existent ones and has more application areas as the lower bound of delay derivative is available.
Finally, some numerical examples can illustrate the reduced conservatism of the derived results by thinning the delay interval.
American Psychological Association (APA)
Zhang, Guobao& Li, Tao& Fei, Shumin. 2011. Further Stability Criterion on Delayed Recurrent Neural Networks Based on Reciprocal Convex Technique. Mathematical Problems in Engineering،Vol. 2012, no. 2012, pp.1-14.
https://search.emarefa.net/detail/BIM-1001980
Modern Language Association (MLA)
Zhang, Guobao…[et al.]. Further Stability Criterion on Delayed Recurrent Neural Networks Based on Reciprocal Convex Technique. Mathematical Problems in Engineering No. 2012 (2012), pp.1-14.
https://search.emarefa.net/detail/BIM-1001980
American Medical Association (AMA)
Zhang, Guobao& Li, Tao& Fei, Shumin. Further Stability Criterion on Delayed Recurrent Neural Networks Based on Reciprocal Convex Technique. Mathematical Problems in Engineering. 2011. Vol. 2012, no. 2012, pp.1-14.
https://search.emarefa.net/detail/BIM-1001980
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1001980