English

Neural Schr\"{o}dinger Equation:Physical Law as Neural Network

Computational Physics 2022-04-05 v2 Optics

Abstract

We show a new family of neural networks based on the Schr\"{o}dinger equation (SE-NET). In this analogy, the trainable weights of the neural networks correspond to the physical quantities of the Schr\"{o}dinger equation. These physical quantities can be trained using the complex-valued adjoint method. Since the propagation of the SE-NET can be described by the evolution of physical systems, its outputs can be computed by using a physical solver. As a demonstration, we implemented the SE-NET using the finite difference method. The trained network is transferable to actual optical systems. Based on this concept, we show a numerical demonstration of end-to-end machine learning with an optical frontend. Our results extend the application field of machine learning to hybrid physical-digital optimizations.

Keywords

Cite

@article{arxiv.2006.13541,
  title  = {Neural Schr\"{o}dinger Equation:Physical Law as Neural Network},
  author = {Mitsumasa Nakajima and Kenji Tanaka and Toshikazu Hashimoto},
  journal= {arXiv preprint arXiv:2006.13541},
  year   = {2022}
}
R2 v1 2026-06-23T16:34:53.020Z