arXiv physics/97050231997-05-19physics.comp-phcomp-gasnlin.CGquant-ph

Artificial Neural Networks for Solving Ordinary and Partial Differential Equations

I. E. Lagaris, A. Likas, D. I. Fotiadis

备注：: LAtex file, 26 pages, 21 figs, submitted to IEEE TNN
DOI：: 10.1109/72.712178

英文摘要：

We present a method to solve initial and boundary value problems using artificial neural networks. A trial solution of the differential equation is written as a sum of two parts. The first part satisfies the boundary (or initial) conditions and contains no adjustable parameters. The second part is constructed so as not to affect the boundary conditions. This part involves a feedforward neural network, containing adjustable parameters (the weights). Hence by construction the boundary conditions are satisfied and the network is trained to satisfy the differential equation. The applicability of this approach ranges from single ODE's, to systems of coupled ODE's and also to PDE's. In this article we illustrate the method by solving a variety of model problems and present comparisons with finite elements for several cases of partial differential equations.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Odeint - Solving ordinary differential equations in C++

Many physical, biological or chemical systems are modeled by ordinary differential equations (ODEs) and finding their solution is an every-day-task for many scientists. Here, we introduce a new C++ library dedicated to find numerical solutions of initial value problems of ODEs: odeint (www.odeint.com). odeint is implemented in a highly generic way and provides extensive interoperability at top performance. For example, due to it's modular design it can be easily parallized with OpenMP and even runs on CUDA GPUs. Despite that, it provides a convenient interface that allows for a simple and easy…

2011-10-15cs.MSnlin.CDphysics.comp-ph

ODEN: A Framework to Solve Ordinary Differential Equations using Artificial Neural Networks

Gonville & Caius College（冈维尔与凯斯学院）；École Normale Supérieure Paris-Saclay（巴黎萨克雷高等师范学院）

We explore in detail a method to solve ordinary differential equations using feedforward neural networks. We prove a specific loss function, which does not require knowledge of the exact solution, to be a suitable standard metric to evaluate neural networks' performance. Neural networks are shown to be proficient at approximating continuous solutions within their training domains. We illustrate neural networks' ability to outperform traditional standard numerical techniques. Training is thoroughly examined and three universal phases are found: (i) a prior tangent adjustment, (ii) a curvature f…

2020-06-01cs.LGphysics.comp-ph

Unsupervised Reservoir Computing for Solving Ordinary Differential Equations

John A. Paulson School of Engineering and Applied Sciences, Harvard University（哈佛大学约翰·A·保尔森工程与应用科学学院）

There is a wave of interest in using unsupervised neural networks for solving differential equations. The existing methods are based on feed-forward networks, {while} recurrent neural network differential equation solvers have not yet been reported. We introduce an unsupervised reservoir computing (RC), an echo-state recurrent neural network capable of discovering approximate solutions that satisfy ordinary differential equations (ODEs). We suggest an approach to calculate time derivatives of recurrent neural network outputs without using backpropagation. The internal weights of an RC are fixe…

2021-08-25cs.LGcs.NEphysics.comp-ph

用于空间实验模拟的常微分方程组自适应并行积分器

An Adaptive Parallel Integrator of Ordinary Differential Equations System for Space Experiment Simulation

Solar Terrestrial Influences Institute, Bulgarian Academy of Sciences（太阳地球影响研究所，保加利亚科学院）

针对空间物体运动预测中常微分方程组求解的计算时间问题，提出一种基于线程并行化和同步方法的自适应并行积分器。

2010-02-16cs.NAmath.NAphysics.comp-ph

使用物理信息神经网络（PINNs）求解刚性常微分方程：改进普通PINNs训练的简单方法

Solving stiff ordinary differential equations using physics informed neural networks (PINNs): simple recipes to improve training of vanilla-PINNs

本文针对普通PINNs难以求解刚性常微分方程初值问题的问题，提出嵌入能量守恒物理、改进初始条件损失定义以及采用增长时间区间和移动配点的渐进式学习等简单改进方法，并验证其对边值问题同样有效。

2023-04-17physics.comp-phphysics.flu-dynphysics.plasm-ph

An efficient method for solving highly oscillatory ordinary differential equations with applications to physical systems

We present a novel numerical routine (oscode) with a C++ and Python interface for the efficient solution of one-dimensional, second-order, ordinary differential equations with rapidly oscillating solutions. The method is based on a Runge-Kutta-like stepping procedure that makes use of the Wentzel-Kramers-Brillouin (WKB) approximation to skip regions of integration where the characteristic frequency varies slowly. In regions where this is not the case, the method is able to switch to a made-to-measure Runge-Kutta integrator that minimises the total number of function evaluations. We demonstrate…

2019-12-13astro-ph.COastro-ph.IMcs.NA

更多相关论文收起更多论文

改进ADER-DG方法中DG预测子的局部解以求解常微分方程组及其对微分代数方程组的适用性

Improving the local solution of the DG predictor of the ADER-DG method for solving systems of ordinary differential equations and its applicability to systems of differential-algebraic equations

Department of Theoretical Physics, Dostoevsky Omsk State University（陀思妥耶夫斯基鄂木斯克国立大学理论物理系）

提出一种改进的ADER-DG方法局部DG预测子，用于求解一阶ODE初值问题，该改进解具有高一阶收敛性和网格节点连续性，并证明其适用于DAE系统。

2026-05-05cs.NAmath.FAmath.NA

On FFT-based convolutions and correlations, with application to solving Poisson's equation in an open rectangular pipe

A new method is presented for solving Poisson's equation inside an open-ended rectangular pipe. The method uses Fast Fourier Transforms (FFTs) to perform mixed convolutions and correlations of the charge density with the Green function. Descriptions are provided for algorithms based on the ordinary Green function and for an integrated Green function (IGF). Due to its similarity to the widely used Hockney algorithm for solving Poisson's equation in free space, this capability can be easily implemented in many existing particle-in-cell beam dynamics codes.

2011-11-21physics.acc-phphysics.comp-ph

Finding Quantum Many-Body Ground States with Artificial Neural Network

Solving ground states of quantum many-body systems has been a long-standing problem in condensed matter physics. Here, we propose a new unsupervised machine learning algorithm to find the ground state of a general quantum many-body system utilizing the benefits of artificial neural network. Without assuming the specific forms of the eigenvectors, this algorithm can find the eigenvectors in an unbiased way with well controlled accuracy. As examples, we apply this algorithm to 1D Ising and Heisenberg models, where the results match very well with exact diagonalization.

2019-06-26cond-mat.dis-nnphysics.comp-phquant-ph

Matrix Lie Maps and Neural Networks for Solving Differential Equations

The coincidence between polynomial neural networks and matrix Lie maps is discussed in the article. The matrix form of Lie transform is an approximation of the general solution of the nonlinear system of ordinary differential equations. It can be used for solving systems of differential equations more efficiently than traditional step-by-step numerical methods. Implementation of the Lie map as a polynomial neural network provides a tool for both simulation and data-driven identification of dynamical systems. If the differential equation is provided, training a neural network is unnecessary. Th…

2019-08-16cs.NAcs.NEmath.DS

One-Shot Transfer Learning of Physics-Informed Neural Networks

University of Oxford（牛津大学）；Harvard University（哈佛大学）

Solving differential equations efficiently and accurately sits at the heart of progress in many areas of scientific research, from classical dynamical systems to quantum mechanics. There is a surge of interest in using Physics-Informed Neural Networks (PINNs) to tackle such problems as they provide numerous benefits over traditional numerical approaches. Despite their potential benefits for solving differential equations, transfer learning has been under explored. In this study, we present a general framework for transfer learning PINNs that results in one-shot inference for linear systems of …

2022-07-05cs.LGphysics.comp-ph

ADER-DG方法用于常微分方程的理论与内部结构

Theory and internal structure of ADER-DG method for ordinary differential equations

Dostoevsky Omsk State University（奥姆斯克国立多斯托耶夫斯基大学）

本文研究了ADER-DG方法在求解常微分方程组中的近似性质、收敛性和稳定性，证明了其多种稳定性特性，并展示了方法的应用与实现。

2026-04-14cs.NAmath.NAmath.SP

New method of solving the many-body Schrödinger equation

A method of solving the Schrödinger equation based on the use of constant particle-particle interaction potential surfaces (IPS) is proposed. The many-body wave function is presented in a configuration interaction form, with coefficients depending on the total interaction potential. The corresponding set of linear ordinary differential equations for the coefficients was developed. To reduce the computational work, a hierarchy of approximations based on interaction potential surfaces of a part of the particle system was worked out. The solution of a simple exactly solvable model and He-like ion…

2016-04-19physics.chem-phphysics.comp-ph

Local Solution Method for Numerical Solving of the Wave Propagation Problem

A new method for numerical solving of boundary problem for ordinary differential equations with slowly varying coefficients which is aimed at better representation of solutions in the regions of their rapid oscillations or exponential increasing (decreasing) is proposed. It is based on approximation of the solution to find in the form of superposition of certain polynomial- exponential basic functions. The method is studied for the Helmholtz equation in comparison with the standard finite difference method. The numerical tests have shown the convergence of the method proposed. In comparison wi…

1999-08-10physics.comp-phphysics.plasm-ph

流体动力学中的人工神经网络：求解纳维-斯托克斯方程的新方法

Artificial Neural Networks in Fluid Dynamics: A Novel Approach to the Navier-Stokes Equations

Austin Peay State University（奥斯汀皮斯州立大学）

本文提出利用神经网络结合贝叶斯聚类和SOM邻域加权方法，基于三维输入数据映射电离层速度场，验证了神经网络在求解湍流纳维-斯托克斯方程中的有效性。

2018-08-19cs.NAcs.NEmath.NA