纳米光子学
计算机科学
分路器
光子学
人工神经网络
深度学习
反向
人工智能
计算机体系结构
电子工程
工程类
光电子学
数学
材料科学
几何学
作者
Keisuke Kojima,Mohammad H. Tahersima,Toshiaki Koike-Akino,Devesh K. Jha,Yingheng Tang,Ye Wang,Kieran Parsons,Fengqiao Sang,Jonathan Klamkin
出处
期刊:Optical Fiber Communication Conference
日期:2020-03-08
被引量:1
标识
DOI:10.1364/ofc.2020.th1a.6
摘要
We present two different approaches to apply deep learning to inverse design for nanophotonic devices. First, we use a regression model, with device parameters as inputs and device responses as outputs, or vice versa. Second, we use a novel generative model to create a series of improved designs. We demonstrate them to design nanophotonic power splitters with multiple splitting ratios.
科研通智能强力驱动
Strongly Powered by AbleSci AI