<ul><li>Utilizing physics-informed neural networks (PINN) to solve partial differential equations (PDEs) becomes a hot issue and also shows its great powers.</li><li>In this paper, a symmetry-enhanced deep neural network (sDNN) is proposed.</li><li>sDNN makes the architecture of neural networks invariant under the finite group.</li><li>Numerical results show that the sDNN outperforms the vanilla PINN with fewer training points and simpler architecture.</li></ul>

Invariant deep neural networks under the finite group for solving partial differential equations

Discover more