Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Co-Design of Free-Space Metasurface Optical Neuromorphic Classifiers for High Performance

Journal Article · · ACS Photonics
 [1];  [2];  [1];  [2];  [2]
  1. Sandia National Lab. (SNL-CA), Livermore, CA (United States)
  2. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
+ Show Author Affiliations

Classification of features in a scene typically requires conversion of the incoming photonic field into the electronic domain. Recently, an alternative approach has emerged whereby passive structured materials can perform classification tasks by directly using free-space propagation and diffraction of light. In this manuscript, we present a theoretical and computational study of such systems and establish the basic features that govern their performance. We show that system architecture, material structure, and input light field are intertwined and need to be co-designed to maximize classification accuracy. Our simulations show that a single layer metasurface can achieve classification accuracy better than conventional linear classifiers, with an order of magnitude fewer diffractive features than previously reported. For a wavelength λ, single layer metasurfaces of size 100λ × 100λ with an aperture density λ–2 achieve ~96% testing accuracy on the MNIST data set, for an optimized distance ~100λ to the output plane. This is enabled by an intrinsic nonlinearity in photodetection, despite the use of linear optical metamaterials. Furthermore, we find that once the system is optimized, the number of diffractive features is the main determinant of classification performance. The slow asymptotic scaling with the number of apertures suggests a reason why such systems may benefit from multiple layer designs. Finally, we show a trade-off between the number of apertures and fabrication noise.

Research Organization:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Sandia National Laboratories, SNL California
Sponsoring Organization:
Defense Advanced Research Projects Agency (DARPA)
Grant/Contract Number:
AC04-94AL85000; NA0003525
OSTI ID:
1810377
Report Number(s):
SAND-2021-7568J; 697239
Journal Information:
ACS Photonics, Vol. 8, Issue 7; ISSN 2330-4022
Publisher:
American Chemical Society (ACS)Copyright Statement
Country of Publication:
United States
Language:
English

References (17)

An energy-efficient high-speed CMOS hybrid comparator with reduced delay time in 40-nm CMOS process journal July 2016
Free-space optical neural network based on thermal atomic nonlinearity journal January 2021
A Resurgence in Neuromorphic Architectures Enabling Remote Sensing Computation conference July 2019
Fourier-space Diffractive Deep Neural Network journal July 2019
Parallel convolutional processing using an integrated photonic tensor core journal January 2021
Gradient-based learning applied to document recognition journal January 1998
All-optical machine learning using diffractive deep neural networks journal July 2018
Class-specific differential detection in diffractive optical neural networks improves inference accuracy journal July 2019
Design framework for metasurface optics-based convolutional neural networks journal January 2021
Analysis of Diffractive Optical Neural Networks and Their Integration With Electronic Neural Networks journal January 2020
Computational inverse design for cascaded systems of metasurface optics journal January 2019
Optical frontend for a convolutional neural network journal January 2019
On classification of distorted images with deep convolutional neural networks conference March 2017
Efficient and effective algorithms for training single-hidden-layer neural networks journal April 2012
Deep learning with coherent nanophotonic circuits journal June 2017
Hybrid optical-electronic convolutional neural networks with optimized diffractive optics for image classification journal August 2018
Approximation by superpositions of a sigmoidal function journal December 1989

Similar Records

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
neural network
optical
classification
metamaterial
artificial intelligence