Abstract
Silicon photonics is a low-cost and versatile platform for various applications. For design of silicon photonic devices, the light-material interaction within its complex subwavelength geometry is difficult to investigate analytically and therefore numerical simulations are majorly adopted. To make the design process more time-efficient and to improve the device performance to its physical limits, various methods have been proposed over the past few years to manipulate the geometries of silicon platform for specific applications. In this review paper, we summarize the design methodologies for silicon photonics including iterative optimization algorithms and deep neural networks. In case of iterative optimization methods, we discuss them in different scenarios in the sequence of increased degrees of freedom: empirical structure, QR-code like structure and irregular structure. We also review inverse design approaches assisted by deep neural networks, which generate multiple devices with similar structure much faster than iterative optimization methods and are thus suitable in situations where piles of optical components are needed. Finally, the applications of inverse design methodology in optical neural networks are also discussed. This review intends to provide the readers with the suggestion for the most suitable design methodology for a specific scenario.
Highlights
Accepted: 14 April 2021Silicon photonics enables massive fabrication of integrated photonic devices at low cost, due to its compatibility with complementary metal oxide semiconductor (CMOS)process [1]
Different from electronic circuits where the versatile functions come from the combination of electronic components, a single silicon photonic device is able to achieve complex functions with delicate geometry design
The difference is that conditional variational autoencoder (CVAE) gets the underlying distribution via encoder and conditional generative adversarial network (CGAN) utilizes a discriminator to judge whether generated geometric parameters share the same distribution with data samples
Summary
Silicon photonics enables massive fabrication of integrated photonic devices at low cost, due to its compatibility with complementary metal oxide semiconductor (CMOS). Iterative optimization algorithms can optimize device geometric parameters for targeted optical performance. Instead of abstracting key parameters that describes device geometry, TO takes the whole design space as a bitmap, where all the pixels are iteratively updated towards the direction of gradient descent until the gradients are small enough. In this way, complex geometric pattern could be quickly generated for a targeted optical performance. Based on the mapping direction between geometric parameters and optical response, DNNs are trained as forward models and inverse models. According to different design goals for a single device or multiple similar devices, we separate the design methodologies into iterative optimization algorithms and DNNs-assisted methods. We point out the challenges of existing design methodologies and highlight a future research direction: inverse designed optical neural networks (ONN)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
