Abstract
This Letter considers a robust stability analysis method for delayed neural networks of neutral type. By constructing a new Lyapunov functional, a novel delay-dependent criterion for the stability is derived in terms of LMIs (linear matrix inequalities). A less conservative stability criterion is derived by using nonlinear properties of the activation function of the neural networks. Two numerical examples are illustrated to show the effectiveness of the proposed method.
| Original language | English |
|---|---|
| Pages (from-to) | 1843-1848 |
| Number of pages | 6 |
| Journal | Physics Letters, Section A: General, Atomic and Solid State Physics |
| Volume | 374 |
| Issue number | 17-18 |
| DOIs | |
| State | Published - 12 Apr 2010 |
Keywords
- Delay-dependent criteria
- LMIs
- Neural networks
- Neutral delay
- Stability