Symbolically Solving Partial Differential Equations using Deep Learning

by   Maysum Panju, et al.

We describe a neural-based method for generating exact or approximate solutions to differential equations in the form of mathematical expressions. Unlike other neural methods, our system returns symbolic expressions that can be interpreted directly. Our method uses a neural architecture for learning mathematical expressions to optimize a customizable objective, and is scalable, compact, and easily adaptable for a variety of tasks and configurations. The system has been shown to effectively find exact or approximate symbolic solutions to various differential equations with applications in natural sciences. In this work, we highlight how our method applies to partial differential equations over multiple variables and more complex boundary and initial value conditions.


page 1

page 2

page 3

page 4


A Neuro-Symbolic Method for Solving Differential and Functional Equations

When neural networks are used to solve differential equations, they usua...

The Multivariate Theory of Functional Connections: Theory, Proofs, and Application in Partial Differential Equations

This article presents a reformulation of the Theory of Functional Connec...

High accuracy power series method for solving scalar, vector, and inhomogeneous nonlinear Schrödinger equations

We develop a high accuracy power series method for solving partial diffe...

A unified deep artificial neural network approach to partial differential equations in complex geometries

We use deep feedforward artificial neural networks to approximate soluti...

Symbolic Solutions of Simultaneous First-order PDEs in One Unknown

We propose and implement an algorithm for solving an overdetermined syst...

Iterative weak approximation and hard bounds for switching diffusion

We establish a novel convergent iteration framework for a weak approxima...

Bayesian Learning to Discover Mathematical Operations in Governing Equations of Dynamic Systems

Discovering governing equations from data is critical for diverse scient...