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

Abstract

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.

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Deep Residual Learning for Image Recognition
• Densely Connected Convolutional Networks
• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
• FractalNet: Ultra-Deep Neural Networks without Residuals
• Machine Learning of Linear Differential Equations using Gaussian Processes
• PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
• Data Driven Governing Equations Approximation Using Deep Neural Networks
• Identity Mappings in Deep Residual Networks
• PDE-Net: Learning PDEs from Data
• Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations
• ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs
• Learning Dynamical Systems and Bifurcation via Group Sparsity

Cited by in corpus (7)

• Data-Driven Deep Learning of Partial Differential Equations in Modal Space
• Attention-Enhanced Neural Network Models for Turbulence Simulation
• Turbulence forecasting via Neural ODE
• Deep Euler method: solving ODEs by approximating the local truncation error of the Euler method
• Discovery of Dynamics Using Linear Multistep Methods
• Characteristic Neural Ordinary Differential Equations
• Neuro-Reachability of Networked Microgrids