Investigation of inverse design of multilayer thin-films with conditional invertible neural networks

In this work, we apply conditional invertible neural networks (cINN) to inversely design multilayer thin-films given an optical target in order to overcome limitations of state-of-the-art optimization approaches. Usually, state-of-the-art algorithms depend on a set of carefully chosen initial thin-f...

Full description

Bibliographic Details

Published in:	Machine Learning: Science and Technology
Main Authors:	Alexander Luce, Ali Mahdavi, Heribert Wankerl, Florian Marquardt
Format:	Article
Language:	English
Published:	IOP Publishing 2023-01-01
Subjects:	conditional invertible neural networks multilayer thin-films inverse design latent space global optimization
Online Access:	https://doi.org/10.1088/2632-2153/acb48d