IEICE TRANSACTIONS on Electronics
Open Access
A Reinforcement Learning Method for Optical Thin-Film Design
-
Full Text Views
49
- Cite this
- Free PDF (3.9MB)
Summary :
Machine learning, especially deep learning, is dramatically changing the methods associated with optical thin-film inverse design. The vast majority of this research has focused on the parameter optimization (layer thickness, and structure size) of optical thin-films. A challenging problem that arises is an automated material search. In this work, we propose a new end-to-end algorithm for optical thin-film inverse design. This method combines the ability of unsupervised learning, reinforcement learning and includes a genetic algorithm to design an optical thin-film without any human intervention. Furthermore, with several concrete examples, we have shown how one can use this technique to optimize the spectra of a multi-layer solar absorber device.
- Publication
- IEICE TRANSACTIONS on Electronics Vol.E105-C No.2 pp.95-101
- Publication Date
- 2022/02/01
- Publicized
- 2021/08/24
- Online ISSN
- 1745-1353
- DOI
- 10.1587/transele.2021ECP5013
- Type of Manuscript
- PAPER
- Category
- Optoelectronics
Authors
Anqing JIANG
Waseda University
Osamu YOSHIE
Waseda University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Anqing JIANG, Osamu YOSHIE, "A Reinforcement Learning Method for Optical Thin-Film Design" in IEICE TRANSACTIONS on Electronics,
vol. E105-C, no. 2, pp. 95-101, February 2022, doi: 10.1587/transele.2021ECP5013.
Abstract: Machine learning, especially deep learning, is dramatically changing the methods associated with optical thin-film inverse design. The vast majority of this research has focused on the parameter optimization (layer thickness, and structure size) of optical thin-films. A challenging problem that arises is an automated material search. In this work, we propose a new end-to-end algorithm for optical thin-film inverse design. This method combines the ability of unsupervised learning, reinforcement learning and includes a genetic algorithm to design an optical thin-film without any human intervention. Furthermore, with several concrete examples, we have shown how one can use this technique to optimize the spectra of a multi-layer solar absorber device.
URL: https://global.ieice.org/en_transactions/electronics/10.1587/transele.2021ECP5013/_p
Copy
@ARTICLE{e105-c_2_95,
author={Anqing JIANG, Osamu YOSHIE, },
journal={IEICE TRANSACTIONS on Electronics},
title={A Reinforcement Learning Method for Optical Thin-Film Design},
year={2022},
volume={E105-C},
number={2},
pages={95-101},
abstract={Machine learning, especially deep learning, is dramatically changing the methods associated with optical thin-film inverse design. The vast majority of this research has focused on the parameter optimization (layer thickness, and structure size) of optical thin-films. A challenging problem that arises is an automated material search. In this work, we propose a new end-to-end algorithm for optical thin-film inverse design. This method combines the ability of unsupervised learning, reinforcement learning and includes a genetic algorithm to design an optical thin-film without any human intervention. Furthermore, with several concrete examples, we have shown how one can use this technique to optimize the spectra of a multi-layer solar absorber device.},
keywords={},
doi={10.1587/transele.2021ECP5013},
ISSN={1745-1353},
month={February},}
Copy
TY - JOUR
TI - A Reinforcement Learning Method for Optical Thin-Film Design
T2 - IEICE TRANSACTIONS on Electronics
SP - 95
EP - 101
AU - Anqing JIANG
AU - Osamu YOSHIE
PY - 2022
DO - 10.1587/transele.2021ECP5013
JO - IEICE TRANSACTIONS on Electronics
SN - 1745-1353
VL - E105-C
IS - 2
JA - IEICE TRANSACTIONS on Electronics
Y1 - February 2022
AB - Machine learning, especially deep learning, is dramatically changing the methods associated with optical thin-film inverse design. The vast majority of this research has focused on the parameter optimization (layer thickness, and structure size) of optical thin-films. A challenging problem that arises is an automated material search. In this work, we propose a new end-to-end algorithm for optical thin-film inverse design. This method combines the ability of unsupervised learning, reinforcement learning and includes a genetic algorithm to design an optical thin-film without any human intervention. Furthermore, with several concrete examples, we have shown how one can use this technique to optimize the spectra of a multi-layer solar absorber device.
ER -
English
