Coupled Ensembles of Neural Networks
Abstract
We present coupled ensembles of neural networks, which is a reconfiguration of existing neural network models into parallel branches. We empirically show that this modification leads to results on CIFAR and SVHN that are competitive to state of the art, with a greatly reduced parameter count. Additionally, for a fixed parameter, or a training time budget coupled ensembles are significantly better than single branch models. Preliminary results on ImageNet are also promising. Code for the experiments can be found at: https://github.com/vabh/ coupled_ensembles
Origin : Files produced by the author(s)
Loading...