Accuracy and Architecture Studies of Residual Neural Network solving Ordinary Differential Equations

Abstract

In this paper we consider utilizing a residual neural network (ResNet) to solve ordinary differential equations. Stochastic gradient descent method is applied to obtain the optimal parameter set of weights and biases of the network. We apply forward Euler, Runge-Kutta2 and Runge-Kutta4 finite difference methods to generate three sets of targets training the ResNet and carry out the target study. The well trained ResNet behaves just as its counterpart of the corresponding one-step finite difference method. In particular, we carry out (1) the architecture study in terms of number of hidden layers and neurons per layer to find the optimal ResNet structure; (2) the target study to verify the ResNet solver behaves as accurate as its finite difference method counterpart; (3) solution trajectory simulation. Even the ResNet solver looks like and is implemented in a way similar to forward Euler scheme, its accuracy can be as high as any one step method. A sequence of numerical examples are presented to demonstrate the performance of the ResNet solver.

References in corpus (11)

• DGM: A deep learning algorithm for solving partial differential equations
• Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
• Data Driven Governing Equations Approximation Using Deep Neural Networks
• Deep learning of dynamics and signal-noise decomposition with time-stepping constraints
• Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems
• MgNet: A Unified Framework of Multigrid and Convolutional Neural Network
• Numerical Aspects for Approximating Governing Equations Using Data
• Variational training of neural network approximations of solution maps for physical models
• Learning across scales - A multiscale method for Convolution Neural Networks
• Robust learning with implicit residual networks
• Discovery of Dynamics Using Linear Multistep Methods