Keywords: neural networks, ensemble learning
TL;DR: We show that splitting a neural network into parallel branches improves performance for a parameter budget.
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: [![github](/images/github_icon.svg) vabh/coupled_ensembles](https://github.com/vabh/coupled_ensembles) + [![Papers with Code](/images/pwc_icon.svg) 1 community implementation](https://paperswithcode.com/paper/?openreview=Hk2MHt-3-)
Data: [CIFAR-10](https://paperswithcode.com/dataset/cifar-10), [CIFAR-100](https://paperswithcode.com/dataset/cifar-100), [SVHN](https://paperswithcode.com/dataset/svhn)
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:1709.06053/code)