SOTAVerified

Augmented Neural ODEs

2019-04-02NeurIPS 2019Code Available1· sign in to hype

Emilien Dupont, Arnaud Doucet, Yee Whye Teh

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

We show that Neural Ordinary Differential Equations (ODEs) learn representations that preserve the topology of the input space and prove that this implies the existence of functions Neural ODEs cannot represent. To address these limitations, we introduce Augmented Neural ODEs which, in addition to being more expressive models, are empirically more stable, generalize better and have a lower computational cost than Neural ODEs.

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
CIFAR-10ANODEPercentage correct60.6Unverified
MNISTAugmented Neural Ordinary Differential EquationPercentage error0.37Unverified
MNISTANODEPercentage error1.8Unverified
SVHNANODEPercentage error16.5Unverified

Reproductions