Coupled Ensembles of Neural Networks - Archive ouverte HAL Access content directly
Conference Papers Year :

Coupled Ensembles of Neural Networks

(1) , (1) , (2)
1
2

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
Fichier principal
Vignette du fichier
iclr2018_workshop.pdf (294.73 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01887644 , version 1 (04-10-2018)

Identifiers

  • HAL Id : hal-01887644 , version 1

Cite

Anuvabh Dutt, Georges Quénot, Denis Pellerin. Coupled Ensembles of Neural Networks. ICLR 2018 - 6th International Conference on Learning Representations - Workshop Track, Apr 2018, Vancouver, Canada. ⟨hal-01887644⟩
119 View
88 Download

Share

Gmail Facebook Twitter LinkedIn More