Share Email Print

Proceedings Paper

Class-specific differential detection in diffractive optical neural networks (Conference Presentation)
Author(s): Jingxi Li; Deniz Mengu; Yi Luo; Yair Rivenson; Aydogan Ozcan

Paper Abstract

We introduce a differential measurement scheme in diffractive neural networks, where object-classes are assigned to separate opto-electronic detector pairs and the class-inference is made based on the maximum normalized differential signal. This scheme enables diffractive networks to achieve blind-testing accuracies of 98.54% and 48.51% for MNIST and CIFAR-10 datasets, respectively. These accuracies improve to 98.52% and 50.82%, when differential detection is combined with the joint-training of parallel diffractive networks, with each specializing on a separate object-class. Finally, we report independently-trained diffractive networks that project their output-light onto a common plane to achieve 98.59% and 51.44%, for the same datasets, respectively.

Paper Details

Date Published: 9 March 2020
Proc. SPIE 11299, AI and Optical Data Sciences, 112990R (9 March 2020); doi: 10.1117/12.2544014
Show Author Affiliations
Jingxi Li, Univ. of California, Los Angeles (United States)
Deniz Mengu, Univ. of California, Los Angeles (United States)
Yi Luo, Univ. of California, Los Angeles (United States)
Yair Rivenson, Univ. of California, Los Angeles (United States)
Aydogan Ozcan, Univ. of California, Los Angeles (United States)

Published in SPIE Proceedings Vol. 11299:
AI and Optical Data Sciences
Bahram Jalali; Ken-ichi Kitayama, 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?