Abstract

Optical computation, especially the optical neural network, has gained great attention recently due to their high computation throughput and low energy consumption. The 2×2 optical processor, as a building block of high-order matrix multiplication circuit, can be an essential part for optical neural networks. For the first time, we demonstrate a compact and general optical processor on silicon-on-isolator platform with a footprint of 1.68×3.6 μm². The transfer matrix of an optical processor is determined by its nanostructured pattern, which has 2⁴²⁰ possible combinations. To accelerate the design process of arbitrary optical processors, a two-step trained tandem model consisting of a forward model and an inverse model based on deep convolutional neural networks is proposed. After training, the forward model is able to predict the transfer matrix for a given optical processor with prediction accuracy of 98.8%, while the calculation speed is more than one thousand times faster than the electromagnetic simulation. The inverse model can predict the geometry of an optical processor for a target transfer matrix with prediction accuracy of 96.5% and its prediction time is also within a second. This two-step trained tandem model paves a new way for optical processors design.

Inverse design paradigm for fast and accurate prediction of a functional metasurface via deep convolutional neural networks

Xudong Du, Chengan Zhou, Hongbai Bai, and Xingxing Liu
Opt. Mater. Express 12(10) 4104-4116 (2022)

Inverse design of plasmonic metasurfaces by convolutional neural network

Ronghui Lin, Yanfen Zhai, Chenxin Xiong, and Xiaohang Li
Opt. Lett. 45(6) 1362-1365 (2020)

Inverse design of a nano-photonic wavelength demultiplexer with a deep neural network approach

Mengwei Yuan, Gang Yang, Shijie Song, Luping Zhou, Robert Minasian, and Xiaoke Yi
Opt. Express 30(15) 26201-26211 (2022)

Inverse design of an on-chip optical response predictor enabled by a deep neural network

Junhyeong Kim, Berkay Neseli, Jae-yong Kim, Jinhyeong Yoon, Hyeonho Yoon, Hyo-hoon Park, and Hamza Kurt
Opt. Express 31(2) 2049-2060 (2023)

Inverse design of polarization conversion metasurfaces by deep neural networks

Wanglei Chen, Runkun Li, Zetian Huang, Hao Wu, Jingyang Wei, Shu Wang, Le Wang, and Yanghui Li
Appl. Opt. 62(8) 2048-2054 (2023)