Evolutionary Feature Selection for Spiking Neural Network Pattern ClassifiersReport as inadecuate




Evolutionary Feature Selection for Spiking Neural Network Pattern Classifiers - Download this document for free, or read online. Document in PDF available to download.

1 Department of Artificial Intelligence, Institute of Applied Informatics 2 FCT-UNL - Faculdade de Ciências e Technologia Lisboa

Abstract : This paper presents an application of the biologically realistic JASTAP neural network model to classification tasks. The JASTAP neural network model is presented as an alternative to the basic multi-layer perceptron model. An evolutionary procedure previously applied to the simultaneous solution of feature selection and neural network training on standard multi-layer perceptrons is extended with JASTAP model. Preliminary results on IRIS standard data set give evidence that this extension allows the use of smaller neural networks that can handle noisier data without any degradation in classification accuracy.





Author: Michal Valko - Nuno Cavalheiro - Marco Castelani -

Source: https://hal.archives-ouvertes.fr/



DOWNLOAD PDF




Related documents