A Method for Representing Periodic Functions and Enforcing Exactly Periodic Boundary Conditions with Deep Neural Networks

by   Suchuan Dong, et al.

We present a simple and effective method for representing periodic functions and enforcing exactly the periodic boundary conditions for solving differential equations with deep neural networks (DNN). The method stems from some simple properties about function compositions involving periodic functions. It essentially composes a DNN-represented arbitrary function with a set of independent periodic functions with adjustable (training) parameters. We distinguish two types of periodic conditions: those imposing the periodicity requirement on the function and all its derivatives (to infinite order), and those imposing periodicity on the function and its derivatives up to a finite order k (k⩾ 0). The former will be referred to as C^∞ periodic conditions, and the latter C^k periodic conditions. We define operations that constitute a C^∞ periodic layer and a C^k periodic layer (for any k⩾ 0). A deep neural network with a C^∞ (or C^k) periodic layer incorporated as the second layer automatically and exactly satisfies the C^∞ (or C^k) periodic conditions. We present extensive numerical experiments on ordinary and partial differential equations with C^∞ and C^k periodic boundary conditions to verify and demonstrate that the proposed method indeed enforces exactly, to the machine accuracy, the periodicity for the DNN solution and its derivatives.


page 19

page 22

page 26


Enforcing exact boundary and initial conditions in the deep mixed residual method

In theory, boundary and initial conditions are important for the wellpos...

Overcoming the order barrier two in splitting methods when applied to semilinear parabolic problems with non-periodic boundary conditions

In general, high order splitting methods suffer from an order reduction ...

Render unto Numerics : Orthogonal Polynomial Neural Operator for PDEs with Non-periodic Boundary Conditions

By learning the map between function spaces using carefully designed dee...

On the convergence of spectral methods involving non-compact operators

Motivated by Fredholm theory, we develop a framework to establish the co...

An Expedient Approach to FDTD-based Modeling of Finite Periodic Structures

This paper proposes an efficient FDTD technique for determining electrom...

Discrete Gradient Flow Approximations of High Dimensional Evolution Partial Differential Equations via Deep Neural Networks

We consider the approximation of initial/boundary value problems involvi...

Please sign up or login with your details

Forgot password? Click here to reset