Generating Neural Networks with Optimal Features through Particle Swarm Optimization

Abstract

In this paper, we propose a new algorithm for generating Neural Network architectures with optimal features through Particle Swarm Optimization. Selecting the best architecture for a Neural Network is usually done through a trial and error process, in which the number of layers is selected usually based on previous experience and then the network is trained and tested. When using Neural Networks as classifiers in feature selection algorithms, usually the number of layers in the Neural Network is selected prior to using the Neural Network as a classifier to the feature selection algorithm. In this paper we propose a new generative algorithm based on PSO which combines the feature selection process with the Neural Network topology selection process in one algorithm which generates the Neural Network topology while at the same time performs feature selection and evaluates the Neural Network topology to determine its quality. With the proposed algorithm, given a dataset, it is possible to end up with the optimal features on the dataset and with an optimal Neural Network classifier for such features.