Share Email Print

Proceedings Paper

Smart design of photonic structures with artificial intelligence and neural networks (Conference Presentation)
Author(s): Wenshan Cai

Paper Abstract

The design and implementation of engineered photonic structures, conventionally, relies on the expertise of a skilled scientist to guide a progression of electromagnetic simulations that iteratively solve Maxwell’s equations until an optimized solution can be achieved. However, the intricate mechanisms and the large degrees of freedom in photonic systems often impede an effective strategy for the design and optimization process. We circumvent this conventional procedure by means of a hybrid artificial intelligence architecture. When fed an input set of customer-defined optical responses, the constructed network generates candidate structures that match the on-demand properties with high fidelity in a systematic manner.

Paper Details

Date Published: 9 March 2020
Proc. SPIE 11284, Smart Photonic and Optoelectronic Integrated Circuits XXII, 1128405 (9 March 2020);
Show Author Affiliations
Wenshan Cai, Georgia Institute of Technology (United States)

Published in SPIE Proceedings Vol. 11284:
Smart Photonic and Optoelectronic Integrated Circuits XXII
Sailing He; Laurent Vivien, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?