RODE-Net: Learning Ordinary Differential Equations with Randomness from Data

no code implementations • 3 Jun 2020 • Junyu Liu, Zichao Long, Ranran Wang, Jie Sun, Bin Dong

To train the RODE-Net, we first estimate the parameters of the unknown RODE using the symbolic networks \cite{long2019pde} by solving a set of deterministic inverse problems based on the measured data, and use a generative adversarial network (GAN) to estimate the true distribution of the RODE's parameters.

Generative Adversarial Network

Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement Learning

1 code implementation • 27 May 2019 • Yufei Wang, Ziju Shen, Zichao Long, Bin Dong

Conservation laws are considered to be fundamental laws of nature.

Decision Making Meta-Learning +2

PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network

2 code implementations • 30 Nov 2018 • Zichao Long, Yiping Lu, Bin Dong

Numerical experiments show that the PDE-Net 2. 0 has the potential to uncover the hidden PDE of the observed dynamics, and predict the dynamical behavior for a relatively long time, even in a noisy environment.

PDE-Net: Learning PDEs from Data

4 code implementations • ICML 2018 • Zichao Long, Yiping Lu, Xianzhong Ma, Bin Dong

In this paper, we present an initial attempt to learn evolution PDEs from data.