论文信息 - Weighted Convolutional Neural Network Ensemble

Weighted Convolutional Neural Network Ensemble

We introduce a new method to combine the output probabilities of convolutional neural networks which we call Weighted Convolutional 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 probabilities to make the predictions. We show the validity of our proposal by improving the classification rate on a common image classification benchmark.

Luís A. Alexandre | Xavier Frazão | Xavier Frazão

[1] Yann LeCun,et al. What is the best multi-stage architecture for object recognition? , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[2] Nitish Srivastava,et al. Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[3] Kunihiko Fukushima,et al. A neural network model for selective attention in visual pattern recognition , 1986, Biological Cybernetics.

[4] Yann LeCun,et al. Regularization of Neural Networks using DropConnect , 2013, ICML.

[5] Patrice Y. Simard,et al. High Performance Convolutional Neural Networks for Document Processing , 2006 .

[6] Alex Krizhevsky,et al. Learning Multiple Layers of Features from Tiny Images , 2009 .

[7] Jürgen Schmidhuber,et al. Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.