Premium
Deep Neural Networks: A Bidirectional Deep Neural Network for Accurate Silicon Color Design (Adv. Mater. 51/2019)
Author(s) -
Gao Li,
Li Xiaozhong,
Liu Dianjing,
Wang Lianhui,
Yu Zongfu
Publication year - 2019
Publication title -
advanced materials
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 10.707
H-Index - 527
eISSN - 1521-4095
pISSN - 0935-9648
DOI - 10.1002/adma.201970364
Subject(s) - artificial neural network , inverse , materials science , tandem , process (computing) , inverse problem , deep neural networks , silicon , computer science , artificial intelligence , algorithm , optoelectronics , mathematics , mathematical analysis , geometry , composite material , operating system
In article number 1905467, to avoid time‐consuming electromagnetic simulation and an iterative optimization process, Li Gao, Zongfu Yu, and co‐workers report the training of a deep neural network that can perform both forward modeling and inverse design of one million different structural colors. The adoption of a tandem network can solve the nonuniqueness problem in the inverse design process with high efficiency and accuracy.