A Neural Network Classifier for Spectral Pattern Recognition. On-Line versus Off-Line Backpropagation Training

Staufer-Steinnocher, Petra and Fischer, Manfred M. (1997) A Neural Network Classifier for Spectral Pattern Recognition. On-Line versus Off-Line Backpropagation Training. Discussion Papers of the Institute for Economic Geography and GIScience, 60/97. WU Vienna University of Economics and Business, Vienna.


Download (317kB)


In this contributon we evaluate on-line and off-line techniques to train a single hidden layer neural network classifier with logistic hidden and softmax output transfer functions on a multispectral pixel-by-pixel classification problem. In contrast to current practice a multiple class cross-entropy error function has been chosen as the function to be minimized. The non-linear diffierential equations cannot be solved in closed form. To solve for a set of locally minimizing parameters we use the gradient descent technique for parameter updating based upon the backpropagation technique for evaluating the partial derivatives of the error function with respect to the parameter weights. Empirical evidence shows that on-line and epoch-based gradient descent backpropagation fail to converge within 100,000 iterations, due to the fixed step size. Batch gradient descent backpropagation training is superior in terms of learning speed and convergence behaviour. Stochastic epoch-based training tends to be slightly more effective than on-line and batch training in terms of generalization performance, especially when the number of training examples is larger. Moreover, it is less prone to fall into local minima than on-line and batch modes of operation. (authors' abstract)

Item Type: Paper
Keywords: Pixel-by-pixel classification / feedforward neural networks / network training / backpropagation / gradient descent technique
Divisions: Departments > Sozioökonomie > Wirtschaftsgeographie und Geoinformatik > Fischer
Depositing User: ePub Administrator
Date Deposited: 20 May 2014 11:12
Last Modified: 17 Feb 2015 09:00
URI: https://epub.wu.ac.at/id/eprint/4152


View Item View Item


Downloads per month over past year

View more statistics