Weighted Convolutional Neural Network Ensemble

Abstract. We introduce a new method to combine the output probabil-ities of convolutional neural networks which we call Weighted Convolu-tional Neural Network Ensemble. Each network has an associated weight that makes networks with better performance have a greater influence at the time to classify in relation to networks that performed worse. This new approach produces better results than the common method that combines the networks doing just the average of the output prob-abilities to make the predictions. We show the validity of our proposal by improving the classification rate on a common image classification benchmark