Co-operative evolution of a neural classifier and feature subset

This paper describes a novel feature selection algorithm which utilizes a genetic algorithm to select a feature subset in conjunction with the weights for a three-layer feedforward network classifier. The algorithm was tested on the "ionosphere" data set from UC Irvine, and on an artifically generated data set. This approach produces results comparable to those reported for other algorithms on the ionosphere data, but using fewer input features and a simpler neural network architecture. These results indicate that tailoring a neural network classifier to a specific subset of features has the potential to produce a classifier with low classification error and good generalizability.