TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Image Classification	Fashion-MNIST	NeuPDE	Percentage error	7.6	# 12
Image Classification	MNIST	NeuPDE	Percentage error	0.51	# 43

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/neupde-neural-network-based-ordinary-and/image-classification-on-fashion-mnist)](https://paperswithcode.com/sota/image-classification-on-fashion-mnist?p=neupde-neural-network-based-ordinary-and)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/neupde-neural-network-based-ordinary-and/image-classification-on-mnist)](https://paperswithcode.com/sota/image-classification-on-mnist?p=neupde-neural-network-based-ordinary-and)`

NeuPDE: Neural Network Based Ordinary and Partial Differential Equations for Modeling Time-Dependent Data

8 Aug 2019 · Yifan Sun, Linan Zhang, Hayden Schaeffer ·

We propose a neural network based approach for extracting models from dynamic data using ordinary and partial differential equations. In particular, given a time-series or spatio-temporal dataset, we seek to identify an accurate governing system which respects the intrinsic differential structure. The unknown governing model is parameterized by using both (shallow) multilayer perceptrons and nonlinear differential terms, in order to incorporate relevant correlations between spatio-temporal samples. We demonstrate the approach on several examples where the data is sampled from various dynamical systems and give a comparison to recurrent networks and other data-discovery methods. In addition, we show that for MNIST and Fashion MNIST, our approach lowers the parameter cost as compared to other deep neural networks.

PDF Abstract