Abstract
This paper discusses the global output convergence of a class of continuous-time recurrent neural networks (RNNs) with globally Lipschitz continuous and monotone nondecreasing activation functions and locally Lipschitz continuous time-varying thresholds. We establish one sufficient condition to guarantee the global output convergence of this class of neural networks. The present result does not require symmetry in the connection weight matrix. The convergence result is useful in the design of recurrent neural networks with time-varying thresholds.
| Original language | English |
|---|---|
| Pages (from-to) | 161-167 |
| Journal | IEEE Transactions on Circuits and Systems II: Express Briefs |
| Volume | 51 |
| Issue number | 4 |
| DOIs | |
| Publication status | Published - Apr 2004 |
| Externally published | Yes |
Research Keywords
- Global output convergence
- Lipschitz continuity
- Lyapunov diagonal semistability
- Neural networks
- Time-varying threshold
Fingerprint
Dive into the research topics of 'Global output convergence of a class of continuous-time recurrent neural networks with time-varying thresholds'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver