Dissecting Neural ODEs
Machine Learning
2021-01-12 v4 Neural and Evolutionary Computing
Machine Learning
Abstract
Continuous deep learning architectures have recently re-emerged as Neural Ordinary Differential Equations (Neural ODEs). This infinite-depth approach theoretically bridges the gap between deep learning and dynamical systems, offering a novel perspective. However, deciphering the inner working of these models is still an open challenge, as most applications apply them as generic black-box modules. In this work we "open the box", further developing the continuous-depth formulation with the aim of clarifying the influence of several design choices on the underlying dynamics.
Cite
@article{arxiv.2002.08071,
title = {Dissecting Neural ODEs},
author = {Stefano Massaroli and Michael Poli and Jinkyoo Park and Atsushi Yamashita and Hajime Asama},
journal= {arXiv preprint arXiv:2002.08071},
year = {2021}
}