bullet Sensors & Transducers Journal

    (ISSN: 2306-8515, e-ISSN 1726-5479)

   

    About this Journal

   Information for Authors

   Editorial Board

   Editorial Calendar

   Current Issue

   Browse Journal

S&T journal's cover

Submit Press Release

Submit White Paper

25 Top Downloaded Articles (2007-2012)

Search

Contact Us

 

 

 

 

Vol. 256, Issue 2, March 2022, pp. 1-11

 

Bullet

 

Learning Binary Data Representation for Optical Processing Units

 

1,* Bogdan Kozyrskiy, 1 Maurizio Filippone, 2 Iacopo Poli, 2,3 Ruben Ohana, 2 Laurent Daudet and 2 Igor Carron

1 Department of Data Science, EURECOM, 450 Route des Chappes, 06410 Biot, France
2 LightOn, 2 rue de la Bourse, F-75002 Paris, France
3 Laboratoire de Physique, Ecole Normale Supérieure, 24 rue Lhomond, 75005 Paris, France
1 Tel.: +33 4 93 00 81 00

* E-mail: Bogdan.Kozyrskiy@eurecom.fr

 

Received: 1 February 2022 /Accepted: 4 March 2022 /Published: 31 March 2022

 

 

Abstract: Optical Processing Units (OPUs) are computing devices that perform random projections of input data by exploiting the physical phenomenon of scattering a light source through a diffusive medium. Random projections calculated by OPUs have been used successfully for approximating kernel ridge regression for large datasets with low power consumption and at high speed. However, OPUs require the input data to be binary. In this paper, we propose to use shallow and deep neural networks (NN) as binary encoders to perform input data binarization. The difficulty in developing a binarization strategy which is learned in an end-to-end fashion along with kernel ridge regression parameters, is due to the non-differentiability of the operation performed by the OPU. We overcome this difficulty by considering OPUs as a black-box and by employing the REINFORCE gradient estimator, which allows us to calculate the gradient of the loss function with respect to the weights of the binarization encoder and to optimize these together with the parameters of kernel ridge regression with gradient- based optimization. Through our experimental campaign on a variety of tasks and datasets, we show that our method outperforms alternative unsupervised and supervised binarization techniques.

 

Keywords: Optimization, Random features, Linear regression, Optical processing unit.

 

Acrobat reader logo Click <here> or title of paper to download the full pages article in pdf format

 

 

This work is licensed under a Creative Commons 4.0 International License

 

 Creative Commons License
 

 

 

 

 


1999 - 2022 Copyright ©, International Frequency Sensor Association (IFSA) Publishing, S.L. All Rights Reserved.


Home - News - Links - Archives - Tools - Voltage-to-Frequency Converters - Standardization - Patents - Marketplace - Projects - Wish List - e-Shop - Sensor Jobs - Membership - Videos - Publishing - Site Map - Subscribe - Search

 Members Area -Sensors Portal -Training Courses - S&T Digest - For advertisers - Bookstore - Forums - Polls - Submit Press Release - Submit White Paper - Testimonies - Twitter - Facebook - LinkedIn