Using Neural Network Ensemble based on Genetic Algorithms to optimize a Semantic Perceptron Net

This paper proposes an approach to construct a better Semantic Perceptron Net (SPN) used for topic spotting. To accomplish this task a learning paradigm call: neural network ensembling is used. Applying this technique to the original structure of Semantic Perceptron Net a new system called GA-SPN (Genetic Algorithm based Semantic Perceptron Net) was developed. The new system uses a neural network ensemble to successfully identify a topic, instead of a single neural network like in the initial system. The neural networks ensemble, one for each topic is built using a selective neural network ensembling technique where only the “best” neural networks join the ensemble.