Enhancing accuracy of physically informed neural networks for nonlinear Schrödinger equations through multi-view transfer learning

Yikai Chen, Hongli Xiao, Xiao Teng, Wenjun Liu, Long Lan

Abstract: Highlights•This study introduces the concept of multi-view transfer learning to the field of PINN.•We examine the impact of different loss functions on PINN training results.•Extensive experiments are conducted to validate the effectiveness of the proposed optimization techniques.

External IDs:dblp:journals/inffus/ChenXTLL24