Abstract
By modifying the Lagrange multipliers, both equality and inequality constraints can be treated identically. Based on this idea, a new type of Lagrange nonlinear programming neural network is constructed, and the stability and convergence of the neural network are analyzed rigorously. Furthermore, the convergence condition of the network is relaxed by the approach of adding the penalty terms in the Lagrangian function.
| Original language | English |
|---|---|
| Pages (from-to) | 27-29 |
| Number of pages | 3 |
| Journal | Tien Tzu Hsueh Pao/Acta Electronica Sinica |
| Volume | 30 |
| Issue number | 1 |
| Publication status | Published - Jan 2001 |
Keywords
- Neural optimization
- Nonlinear programming
- Stability