English

Classification with Runge-Kutta networks and feature space augmentation

Machine Learning 2021-10-08 v2 Dynamical Systems

Abstract

In this paper we combine an approach based on Runge-Kutta Nets considered in [Benning et al., J. Comput. Dynamics, 9, 2019] and a technique on augmenting the input space in [Dupont et al., NeurIPS, 2019] to obtain network architectures which show a better numerical performance for deep neural networks in point and image classification problems. The approach is illustrated with several examples implemented in PyTorch.

Keywords

Cite

@article{arxiv.2104.02369,
  title  = {Classification with Runge-Kutta networks and feature space augmentation},
  author = {Elisa Giesecke and Axel Kröner},
  journal= {arXiv preprint arXiv:2104.02369},
  year   = {2021}
}
R2 v1 2026-06-24T00:52:48.372Z