Training guidelines for neural networks to estimate stability regions

Enrique D. Ferreira; Bruce H. Krogh

Training guidelines for neural networks to estimate stability regions

Enrique D. Ferreira
, Bruce H. Krogh

Carnegie Mellon University

Research output: Contribution to journal › Conference article › peer-review

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.

Original language	English
Pages (from-to)	2829-2833
Number of pages	5
Journal	Proceedings of the American Control Conference
Volume	4
State	Published - 1999
Externally published	Yes
Event	Proceedings of the 1999 American Control Conference (99ACC) - San Diego, CA, USA Duration: 2 Jun 1999 → 4 Jun 1999

Cite this

@article{cf5ac95a45c1459999dabd1def24c15b,

title = "Training guidelines for neural networks to estimate stability regions",

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.",

author = "Ferreira, \{Enrique D.\} and Krogh, \{Bruce H.\}",

year = "1999",

language = "Ingl{\'e}s",

volume = "4",

pages = "2829--2833",

journal = "Proceedings of the American Control Conference",

issn = "0743-1619",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "Proceedings of the 1999 American Control Conference (99ACC) ; Conference date: 02-06-1999 Through 04-06-1999",

}

TY - JOUR

T1 - Training guidelines for neural networks to estimate stability regions

AU - Ferreira, Enrique D.

AU - Krogh, Bruce H.

PY - 1999

Y1 - 1999

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/0033285446

M3 - Artículo de la conferencia

AN - SCOPUS:0033285446

SN - 0743-1619

VL - 4

SP - 2829

EP - 2833

JO - Proceedings of the American Control Conference

JF - Proceedings of the American Control Conference

T2 - Proceedings of the 1999 American Control Conference (99ACC)

Y2 - 2 June 1999 through 4 June 1999

ER -

Training guidelines for neural networks to estimate stability regions

Abstract

Other files and links

Fingerprint

Cite this