2007 Special Issue: Reducing uncertainties in neural network Jacobians and improving accuracy of neural network emulations with NN ensemble approaches

Authors:
Vladimir M. Krasnopolsky
Affiliations:
Science Applications International Corporation at Environmental Modeling Center, National Centers for Environmental Prediction, National Oceanic and Atmospheric Administration, MD, USA and Earth S ...
Venue:
Neural Networks
Year:
2007

Citing 8
Cited 0

On the approximate realization of continuous mappings by neural networks

Neural Networks
Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks

Neural Networks
The nature of statistical learning theory

The nature of statistical learning theory
Optimal linear combinations of neural networks

Neural Networks
Ensemble modelling or selecting the best model: Many could be better than one

Artificial Intelligence for Engineering Design, Analysis and Manufacturing
2006 Special issue: Complex hybrid models combining deterministic and machine learning components for numerical climate modeling and weather prediction

Neural Networks - 2006 special issue: Earth sciences and environmental applications of computational intelligence
Combining the predictions of multiple classifiers: using competitive learning to initialize neural networks

IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 1
The “weight smoothing” regularization of MLP for Jacobian stabilization

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new application of the NN ensemble technique to improve the accuracy (reduce uncertainty) of NN emulation Jacobians is presented. It is shown that the introduced ensemble technique can be successfully applied to significantly reduce uncertainties in NN emulation Jacobians and to reach the accuracy of NN Jacobian calculations that is sufficient for the use in data assimilation systems. An NN ensemble approach is also applied to improve the accuracy of NN emulations themselves. Two ensembles linear (or conservative) and nonlinear (uses an additional averaging NN to calculate the ensemble average) were introduced and compared. The ensemble approaches: (a) significantly reduce the systematic and random error in NN emulation Jacobian, (b) significantly reduce the magnitudes of the extreme outliers and, (c) in general, significantly reduce the number of larger errors. It is also shown that the nonlinear ensemble is able to account for nonlinear correlations between ensemble members and to improve significantly the accuracy of the NN emulation as compared to the linear conservative ensemble in terms of systematic (bias), random, and larger errors.