Inverse Design of Nanophotonic Devices using Deep Neural Networks

Kojima, K.; Tang, Yingheng; Koike‐Akino, Toshiaki; Wang, Ye; Jha, Devesh K.; Parsons, Kieran; Tahersima, Mohammad H.; Sang, Fengqiao; Klamkin, Jonathan; Qi, Minghao

doi:10.1364/acpc.2020.su1a.1

Cited by 3 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This allows a trained system to be able to either analyze or generate structures without needing time-intensive numerical simulations. Different ML and ANN techniques, such as convolutional neural networks (CNNs), , deep neural networks (DNNs), , and generative adversarial networks (GANs) , have been explored for the forward − and inverse design ,,,− of nanophotonic structures. Moreover, recent works have investigated the use of pretrained networks − in photonic applications, showing the promise of transfer learning as well.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning in Interpolation and Extrapolation for Nanophotonic Inverse Design

Acharige

Johlin

2022

ACS Omega

View full text Add to dashboard Cite

The algorithmic design of nanophotonic structures promises to significantly improve the efficiency of nanophotonic components due to the strong dependence of electromagnetic function on geometry and the unintuitive connection between structure and response. Such approaches, however, can be highly computationally intensive and do not ensure a globally optimal solution. Recent theoretical results suggest that machine learning techniques could address these issues as they are capable of modeling the response of nanophotonic structures at orders of magnitude lower time per result. In this work, we explore the utilization of artificial neural network (ANN) techniques to improve the algorithmic design of simple absorbing nanophotonic structures. We show that different approaches show various aptitudes in interpolation versus extrapolation, as well as peak performances versus consistency. Combining ANNs with classical machine learning techniques can outperform some standard ANN techniques for forward design, both in terms of training speed and accuracy in interpolation, but extrapolative performance can suffer. Networks pretrained on general image classification perform well in predicting optical responses of both interpolative and extrapolative structures, with very little additional training time required. Furthermore, we show that traditional deep neural networks are able to perform significantly better in extrapolation than more complicated architectures using convolutional or autoencoder layers. Finally, we show that such networks are able to perform extrapolation tasks in structure generation to produce structures with spectral responses significantly outside those of the structures on which they are trained.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine Learning in Interpolation and Extrapolation for Nanophotonic Inverse Design

Acharige

Johlin

2022

ACS Omega

View full text Add to dashboard Cite

show abstract

“…Currently, inverse design problems can be solved by using several techniques, with the most common being genetic algorithms and adjoint methods [6].While having their own strengths and weaknesses, both are computationally expensive and non-trivial to implement, and neither can ensure a globally optimal solution. However, recent theoretical results show that machine learning (ML) and artificial neural network (ANN) techniques are capable of modeling nanophotonic structures for nanophotonic devices, at orders of magnitude lower time per result [7][8][9][10][11].Specifically, neural networks have been used for both forward design [12][13][14][15] and inverse design [7,[16][17][18][19][20][21][22] of nanophotonic structures.…”

Section: Introductionmentioning

confidence: 99%

Machine learning and artificial neural networks for improved algorithmic design of nanophotonic structures

Acharige

Johlin

2021

Proceedings of the Canadian Conference on Artificial Intelligence

View full text Add to dashboard Cite

Advances in machine learning optimization for classical and quantum photonics

Sanchez,

Everly,

Postigo

2024

J. Opt. Soc. Am. B

View full text Add to dashboard Cite

The development and optimization of photonic devices and various other nanostructure electromagnetic devices present a computationally intensive task. Much optimization relies on finite-difference time-domain or finite element analysis simulations, which can become very computationally demanding for finely detailed structures and dramatically reduce the available optimization space. In recent years, various inverse design machine learning (ML) techniques have been successfully applied to realize previously unexplored optimization spaces for photonic and quantum photonic devices. In this review, recent results using conventional optimization methods, such as the adjoint method and particle swarm, are examined along with ML optimization using convolutional neural networks, Bayesian optimizations with deep learning, and reinforcement learning in the context of new applications to photonics and quantum photonics.

show abstract

Inverse Design of Nanophotonic Devices using Deep Neural Networks

Cited by 3 publications

References 3 publications

Machine Learning in Interpolation and Extrapolation for Nanophotonic Inverse Design

Machine Learning in Interpolation and Extrapolation for Nanophotonic Inverse Design

Machine learning and artificial neural networks for improved algorithmic design of nanophotonic structures

Advances in machine learning optimization for classical and quantum photonics

Contact Info

Product

Resources

About