Share Email Print

Proceedings Paper

Challenges and opportunities for optical neural network (Conference Presentation)
Author(s): Arka Majumdar

Paper Abstract

The parallelism of optics and the miniaturization of optical components using nanophotonic structures, such as metasurfaces, present a compelling alternative to electronic implementations of convolutional neural networks. The lack of a low-power optical nonlinearity, however, requires slow and energy-inefficient conversions between the electronic and optical domains. Here, we design an architecture that utilizes a single electrical to optical conversion by designing a free-space optical frontend unit that implements the linear operations of the first layer with the subsequent layers realized electronically. Speed and power analysis of the architecture indicates that the hybrid photonic–electronic architecture outperforms a fully electronic architecture for large image sizes and kernels. We also explore the ways the nonlinearity can be implemented in optical domain, and analyze the performance of a degenerate cavity for nonlinear image processing.

Paper Details

Date Published: 24 March 2020
Proc. SPIE 11329, Advanced Etch Technology for Nanopatterning IX, 113290P (24 March 2020);
Show Author Affiliations
Arka Majumdar, Univ. of Washington (United States)

Published in SPIE Proceedings Vol. 11329:
Advanced Etch Technology for Nanopatterning IX
Richard S. Wise; Catherine B. Labelle, 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?