Multi-objective and categorical global optimization of photonic structures based on ResNet generative neural networks

TL;DR

This paper introduces a deep generative neural network approach based on GLOnets for efficient multi-objective and categorical global optimization of photonic structures, demonstrating significant speed improvements over traditional methods.

Contribution

The paper presents a novel residual network-based GLOnet framework capable of optimizing complex photonic devices across multiple objectives and categories, with demonstrated success in design tasks.

Findings

GLOnets can find global optima orders of magnitude faster than conventional algorithms.

The method successfully designs thin film stacks with multiple materials.

Application to light filters shows practical utility in complex photonic design.

Abstract

We show that deep generative neural networks, based on global topology optimization networks (GLOnets), can be configured to perform the multi-objective and categorical global optimization of photonic devices. A residual network scheme enables GLOnets to evolve from a deep architecture, which is required to properly search the full design space early in the optimization process, to a shallow network that generates a narrow distribution of globally optimal devices. As a proof-of-concept demonstration, we adapt our method to design thin film stacks consisting of multiple material types. Benchmarks with known globally-optimized anti-reflection structures indicate that GLOnets can find the global optimum with orders of magnitude faster speeds compared to conventional algorithms. We also demonstrate the utility of our method in complex design tasks with its application to incandescent light filters. These results indicate that advanced concepts in deep learning can push the capabilities of inverse design algorithms for photonics.