papers AI Learner
The Github is limit! Click to go to the new site.

Joint Training of Neural Network Ensembles

2019-02-12
Andrew M. Webb, Charles Reynolds, Dan-Andrei Iliescu, Henry Reeve, Mikel Lujan, Gavin Brown

Abstract

We examine the practice of joint training for neural network ensembles, in which a multi-branch architecture is trained via single loss. This approach has recently gained traction, with claims of greater accuracy per parameter along with increased parallelism. We introduce a family of novel loss functions generalizing multiple previously proposed approaches, with which we study theoretical and empirical properties of joint training. These losses interpolate smoothly between independent and joint training of predictors, demonstrating that joint training has several disadvantages not observed in prior work. However, with appropriate regularization via our proposed loss, the method shows new promise in resource limited scenarios and fault-tolerant systems, e.g., IoT and edge devices. Finally, we discuss how these results may have implications for general multi-branch architectures such as ResNeXt and Inception.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1902.04422

PDF

http://arxiv.org/pdf/1902.04422


Similar Posts

Comments