Training Guidelines for Neural Networks to Estimate Stability Regions
Conference Paper, Proceedings of American Control Conference (ACC '99), Vol. 4, pp. 2829 - 2833, June, 1999
Abstract
This paper presents new results on the use of neural networks to estimate stability regions for autonomous nonlinear systems. In contrast to model-based analytical methods, this approach uses empirical data from the system to train the neural network. A method is developed to generate confidence intervals for the regions identified by the trained neural network. The neural network results are compared with estimates obtained by previously proposed methods for a standard two-dimensional example.
BibTeX
@conference{Ferreira-1999-14936,author = {Enrique Ferreira and Bruce Krogh},
title = {Training Guidelines for Neural Networks to Estimate Stability Regions},
booktitle = {Proceedings of American Control Conference (ACC '99)},
year = {1999},
month = {June},
volume = {4},
pages = {2829 - 2833},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.