Stability analysis of neural net control
โ
Thomas Feuring; James J. Buckley; Wolfram-M. Lippe; Andreas Tenhagen
๐
Article
๐
1999
๐
Elsevier Science
๐
English
โ 810 KB
Neural networks can only be trained with a crisp and finite data set. Therefore, the approximation quality of a trained network is hard to verify. So, a common way in proving stability of a trained neural net controller is to demonstrate the existence of a Lyapunov function. In this article we propo