Abstract
This paper presents a new result on absolute exponential stability (AEST) of a class of continuous-time recurrent neural networks with locally Lipschitz continuous and monotone nondecreasing activation functions. The additively diagonally stable connection weight matrices are proven to be able to guarantee AEST of the neural networks. The AEST result extends and improves the existing absolute stability and AEST ones in the literature. © 2003 IEEE.
| Original language | English |
|---|---|
| Pages (from-to) | 35-45 |
| Journal | IEEE Transactions on Neural Networks |
| Volume | 14 |
| Issue number | 1 |
| Online published | 31 Jan 2003 |
| DOIs | |
| Publication status | Published - Jan 2003 |
| Externally published | Yes |
Research Keywords
- Absolute exponential stability (AEST)
- Additive diagonal stability
- Diagonal semistability
- Global exponential stability
- H-matrix
- Neural networks
Fingerprint
Dive into the research topics of 'Absolute exponential stability of a class of continuous-time recurrent neural networks'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver