Committees of deep feedforward networks trained with few data

Bogdan Miclut, Thomas Kaester, Thomas Martinetz, Erhardt Barth

Abstract

Deep convolutional neural networks are known to give good results on image classification tasks. In this paper we present a method to improve the classification result by combining multiple such networks in a committee. We adopt the STL-10 dataset which has very few training examples and show that our method can achieve results that are better than the state of the art. The networks are trained layer-wise and no backpropagation is used. We also explore the effects of dataset augmentation by mirroring, rotation, and scaling.

Results

TaskDatasetMetricValueModel
Image ClassificationSTL-10Percentage correct68DFF Committees

Related Papers