LMI-based approach for asymptotically stability analysis of delayed neural networks

By X. Liao, Guanrong Chen, Edgar N. Sánchez. 2002

352 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Computer Networks and Communications

View Paper: https://www.semanticscholar.org/paper/df636542f1e4f08e29420b195e32bba765582a01

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Derong Liu
2. Zidong Wang
3. Huaguang Zhang
4. Xiaohui Liu
5. D.W.C. Ho
6. Zhanshan Wang
7. Ding Wang
8. Qinglai Wei

In Computational Theory and Mathematics

1. Derong Liu
2. Huaguang Zhang
3. Zidong Wang
4. D.W.C. Ho
5. Zhanshan Wang
6. Xiaohui Liu
7. Qinglai Wei
8. Frank L. Lewis

In Computer Networks and Communications

1. Zidong Wang
2. Xiaohui Liu
3. Huaguang Zhang
4. Zhanshan Wang
5. Derong Liu
6. D.W.C. Ho
7. Huijun Gao
8. Qing-Long Han

Citations in the corpus

• State estimation for delayed neural networks (2005, background): “The stability analysis problem for the delayed neural network of the type (24) has attracted significant research interests [1], [4], [10]–[12].”
• A Comprehensive Review of Stability Analysis of Continuous-Time Recurrent Neural Networks (2014, methodology): “Since 2002 [162], [163], the linear matrix inequality (LMI) method has been used in the stability analysis of recurrent neural”
• Global Asymptotic Stability of Recurrent Neural Networks With Multiple Time-Varying Delays (2008, methodology): “is in the same form as the condition in [17, Th. 1]. (Note that the matrix in [17, Th. 1] is positive definite.) Obviously, is only a sufficient condition to ensure , where we have used the fact that is equivalent to for nonsingular matrix . In the case of being a diagonal matrix, Theorem 1 in [ 17 ”