Deep neural networks for the evaluation and design of photonic devices

TL;DR

This paper explores how deep neural networks can revolutionize photonic device design and evaluation by serving as fast surrogate models, learning geometric features, and optimizing device configurations.

Contribution

It introduces the application of deep neural networks as surrogate electromagnetic solvers and global optimizers in photonics, highlighting their potential for rapid and accurate device design.

Findings

Neural networks can act as high-speed electromagnetic solvers.

Deep generative networks can learn geometric features of photonic devices.

Neural networks can be used as robust global optimizers in photonics design.

Abstract

The data sciences revolution is poised to transform the way photonic systems are simulated and designed. Photonics are in many ways an ideal substrate for machine learning: the objective of much of computational electromagnetics is the capture of non-linear relationships in high dimensional spaces, which is the core strength of neural networks. Additionally, the mainstream availability of Maxwell solvers makes the training and evaluation of neural networks broadly accessible and tailorable to specific problems. In this Review, we will show how deep neural networks, configured as discriminative networks, can learn from training sets and operate as high-speed surrogate electromagnetic solvers. We will also examine how deep generative networks can learn geometric features in device distributions and even be configured to serve as robust global optimizers. Fundamental data sciences concepts framed within the context of photonics will also be discussed, including the network training process, delineation of different network classes and architectures, and dimensionality reduction.