Abstract
The purpose of this paper is to introduce Variable Structure-based-on-line learning algorithms for continuous time two layer and three layer perceptron networks with non-linear and linear activation functions. The computer implementation of the proposed algorithms result in a temporal learning capabilities of a neural network with dynamically adjusted weights, and zero convergence of the learning error in a finite time. The performance of the considered networks is tested in terms of solving a tracking problem of a sine signal.
| Original language | English (US) |
|---|---|
| Pages | 548-552 |
| Number of pages | 5 |
| State | Published - 1996 |
| Externally published | Yes |
| Event | Proceedings of the 1996 IEEE International Symposium on Intelligent Control - Dearborn, MI, USA Duration: Sep 15 1996 → Sep 18 1996 |
Other
| Other | Proceedings of the 1996 IEEE International Symposium on Intelligent Control |
|---|---|
| City | Dearborn, MI, USA |
| Period | 9/15/96 → 9/18/96 |
ASJC Scopus subject areas
- Control and Systems Engineering
- Modeling and Simulation
- Computer Science Applications
- Electrical and Electronic Engineering