A service provided by the WU Library and the WU IT-Services

Optimization in an Error Backpropagation Neural Network Environment with a Performance Test on a Pattern Classification Problem

Fischer, Manfred M. and Staufer-Steinnocher, Petra (1998) Optimization in an Error Backpropagation Neural Network Environment with a Performance Test on a Pattern Classification Problem. Discussion Papers of the Institute for Economic Geography and GIScience, 62/98. WU Vienna University of Economics and Business, Vienna.

[img]
Preview
PDF
Download (564Kb) | Preview

Abstract

Various techniques of optimizing the multiple class cross-entropy error function to train single hidden layer neural network classifiers with softmax output transfer functions are investigated on a real-world multispectral pixel-by-pixel classification problem that is of fundamental importance in remote sensing. These techniques include epoch-based and batch versions of backpropagation of gradient descent, PR-conjugate gradient and BFGS quasi-Newton errors. The method of choice depends upon the nature of the learning task and whether one wants to optimize learning for speed or generalization performance. It was found that, comparatively considered, gradient descent error backpropagation provided the best and most stable out-of-sample performance results across batch and epoch-based modes of operation. If the goal is to maximize learning speed and a sacrifice in generalisation is acceptable, then PR-conjugate gradient error backpropagation tends to be superior. If the training set is very large, stochastic epoch-based versions of local optimizers should be chosen utilizing a larger rather than a smaller epoch size to avoid inacceptable instabilities in the generalization results. (authors' abstract)

Item Type: Paper
Additional Information: Published in: Geographical Analysis , Vol. 31, No. 3 (1999): pp. 89-108.
Keywords: Feedforward Neural Network Training / Numerical Optimization Techniques / Error Backpropagation / Cross-Entropy Error Function / Multispectral Pixel-by-Pixel Classification
Divisions: Departments > Sozioökonomie > Wirtschaftsgeographie und Geoinformatik > Fischer
Depositing User: ePub Administrator
Date Deposited: 20 May 2014 12:25
Last Modified: 08 Apr 2017 19:20
FIDES Link: https://bach.wu.ac.at/d/research/results/7628/
URI: http://epub.wu.ac.at/id/eprint/4150

Actions

View Item