Evolutionary feature selection for spiking neural network pattern classifiers

TL;DR

This paper applies an evolutionary feature selection method to a biologically realistic neural network model, JASTAP, demonstrating improved efficiency and noise robustness in classification tasks.

Contribution

It extends an evolutionary feature selection approach to the JASTAP neural network, an alternative to traditional multi-layer perceptrons.

Findings

Smaller neural networks achieved with JASTAP.

JASTAP handles noisier data without accuracy loss.

Preliminary results on IRIS dataset support effectiveness.

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.