Neural network classification: maximizing zero-error density

Authors:
Luís M. Silva;Luís A. Alexandre;J. Marques de Sá
Affiliations:
INEB -Instituto de Engenharia Biomédica, Lab. de Sinal e Imagem Biomédica, Porto, Portugal;INEB -Instituto de Engenharia Biomédica, Lab. de Sinal e Imagem Biomédica, Porto, Portugal;INEB -Instituto de Engenharia Biomédica, Lab. de Sinal e Imagem Biomédica, Porto, Portugal
Venue:
ICAPR'05 Proceedings of the Third international conference on Advances in Pattern Recognition - Volume Part I
Year:
2005

Citing 3
Cited 1

Adaptive mixtures of local experts

Neural Computation
An error-entropy minimization algorithm for supervised training ofnonlinear adaptive systems

IEEE Transactions on Signal Processing
Generalized information potential criterion for adaptive system training

IEEE Transactions on Neural Networks

Data classification with multilayer perceptrons using a generalized error function

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a new cost function for neural network classification: the error density at the origin. This method provides a simple objective function that can be easily plugged in the usual backpropagation algorithm, giving a simple and efficient learning scheme. Experimental work shows the effectiveness and superiority of the proposed method when compared to the usual mean square error criteria in four well known datasets.