TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Image Classification	CIFAR-10	ANODE	Percentage correct	60.6	# 225
Image Classification	MNIST	Augmented Neural Ordinary Differential Equation	Percentage error	0.37	# 21
Image Classification	MNIST	Augmented Neural Ordinary Differential Equation	Accuracy	99.63	# 14
Image Classification	MNIST	ANODE	Percentage error	1.8	# 73
Image Classification	MNIST	ANODE	Accuracy	98.2	# 23
Image Classification	SVHN	ANODE	Percentage error	16.5	# 48

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/augmented-neural-odes/image-classification-on-mnist)](https://paperswithcode.com/sota/image-classification-on-mnist?p=augmented-neural-odes)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/augmented-neural-odes/image-classification-on-svhn)](https://paperswithcode.com/sota/image-classification-on-svhn?p=augmented-neural-odes)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/augmented-neural-odes/image-classification-on-cifar-10)](https://paperswithcode.com/sota/image-classification-on-cifar-10?p=augmented-neural-odes)`

Augmented Neural ODEs

NeurIPS 2019 · Emilien Dupont, Arnaud Doucet, Yee Whye Teh ·

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.

PDF Abstract NeurIPS 2019 PDF NeurIPS 2019 Abstract

Code

Add Remove Mark official

EmilienDupont/augmented-neural-odes official

517

mitmath/18S096SciML

303

locuslab/monotone_op_net

mandubian/pytorch-neural-ode

kfallah/NODE-Denoiser

See all 6 implementations

Tasks

Add Remove

Image Classification

Datasets

CIFAR-10

MNIST

SVHN

Results from the Paper

Edit

Ranked #21 on Image Classification on MNIST

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Image Classification	CIFAR-10	ANODE	Percentage correct	60.6	# 225	Compare
Image Classification	MNIST	Augmented Neural Ordinary Differential Equation	Percentage error	0.37	# 21	Compare
Image Classification	MNIST	Augmented Neural Ordinary Differential Equation	Accuracy	99.63	# 14	Compare
Image Classification	MNIST	ANODE	Percentage error	1.8	# 73	Compare
Image Classification	MNIST	ANODE	Accuracy	98.2	# 23	Compare
Image Classification	SVHN	ANODE	Percentage error	16.5	# 48	Compare

Methods

Add Remove

No methods listed for this paper. Add relevant methods here

Edit Social Preview

Augmented Neural ODEs

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove