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

Abstract

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-film parameters or employ neural networks which must be retrained for every new application. We aim to overcome those limitations by training the cINN to learn the loss landscape of all thin-film configurations within a training dataset. We show that cINNs can generate a stochastic ensemble of proposals for thin-film configurations that are reasonably close to the desired target depending only on random variables. By refining the proposed configurations further by a local optimization, we show that the generated thin-films reach the target with significantly greater precision than comparable state-of-the-art approaches. Furthermore, we tested the generative capabilities on samples which are outside of the training data distribution and found that the cINN was able to predict thin-films for out-of-distribution targets, too. The results suggest that in order to improve the generative design of thin-films, it is instructive to use established and new machine learning methods in conjunction in order to obtain the most favorable results.

Transfer Learning-Assisted Inverse Modeling in Nanophotonics Based on Mixture Density Networks

“…Photonics, a multidisciplinary field that encompasses the study and manipulation of light, has witnessed profound transformations thanks to ML techniques. ML techniques have been proposed in the literature for the modeling and design optimization of photonic devices [1]- [16]. Deep neural networks (DNNs) are frequently employed, utilizing functions constructed by combining multiple layers of affine transformations and non-linear activation functions, which allows modeling intricate patterns in a data-centric manner.…”

“…In the case of photonics modeling, the optical response is often represented by the wavelength-dependent response sampled at a set of wavelength values. Multiple techniques have been proposed for the inverse modeling [4], [6], [14]- [16]. An inverse modeling approach avoids the need for coupling a forward model with an optimizer and directly performs the prediction of the optimal design parameters values.…”

Wide-Angular Tolerance Optical Filter Design and Its Application to Green Pepper Segmentation

“…A number of studies (e.g., needle optimization [ 13 ], admittance diagram, inverse design [ 14 , 15 ], and reinforcement learning [ 16 , 17 ]) have been proposed and published that describe optical filter design for specific problems. Due to the importance of optical filters, much research in recent years has focused on designing the wide-angle optical filter to eliminate the distortion of spectral transmission of light.…”