Evolutionary feature selection for spiking neural network pattern classifiers
Incremental extension of existing evolutionary feature selection to a different neural network model for classification tasks.
The paper extends an evolutionary feature selection method to the JASTAP spiking neural network model for classification, achieving smaller networks that handle noisier data without accuracy loss on the IRIS dataset.
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.