Error Estimation by Series Association for Neural Network Systems
Authors:
- 1 July 1995
- journal article
- Published by MIT Press in Neural Computation
- Vol. 7 (4) , 799-808
Abstract
Estimation of confidence intervals for neural network outputs is important when the uncertainty of a neural network system must be addressed for safety or reliability. This paper presents a new approach for estimating confidence intervals, which can help users validate neural network outputs. The estimation of confidence intervals, called error estimation by series association, is performed by a supplementary neural network trained to predict the error of the main neural network using input features and the output of the main network. The accuracy of this approach is shown using a simple nonlinear mapping and more complicated, realistic nuclear power plant fault diagnosis problems. The results demonstrate that the approach performs confidence estimation successfully.Keywords
This publication has 9 references indexed in Scilit:
- Error Prediction for a Nuclear Power Plant Fault-Diagnostic Advisor Using Neural NetworksNuclear Technology, 1994
- Nuclear Power Plant Status Diagnostics Using an Artificial Neural NetworkNuclear Technology, 1992
- Application of Neural Networks for Sensor Validation and Plant MonitoringNuclear Technology, 1992
- Stacked generalizationNeural Networks, 1992
- Kolmogorov's theorem and multilayer neural networksNeural Networks, 1992
- Use of neural nets for dynamic modeling and control of chemical process systemsComputers & Chemical Engineering, 1990
- A neural network methodology for process fault diagnosisAIChE Journal, 1989
- From Stein's Unbiased Risk Estimates to the Method of Generalized Cross ValidationThe Annals of Statistics, 1985
- The Predictive Sample Reuse Method with ApplicationsJournal of the American Statistical Association, 1975