Classification with Runge-Kutta networks and feature space augmentation
This work addresses classification accuracy for machine learning practitioners, but it is incremental as it combines existing methods.
The paper tackles the problem of improving deep neural network performance in point and image classification by combining Runge-Kutta Nets with feature space augmentation, resulting in better numerical performance as demonstrated through examples.
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.