An optical neural chip for implementing complex-valued neural network

Complex-valued neural networks have many advantages over their real-valued counterparts. Conventional digital electronic computing platforms are incapable of executing truly complex-valued representations and operations. In contrast, optical computing platforms that encode information in both phase...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhang, Hui, Gu, Mile, Jiang, Xudong, Thompson, Jayne, Cai, Hong, Paesani‬‪, Stefano, Santagati, ‪Raffaele, Laing, ‪Anthony, Zhang, Yi, Yung, Man Hong, Shi, Yuzhi, Muhammad Faeyz Karim, Lo, Guo Qiang, Luo, Xian Shu, Dong, Bin, Kwong, Dim Lee, Kwek, Leong Chuan, Liu, Ai Qun
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2021
Subjects:
Online Access:https://hdl.handle.net/10356/151455
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-151455
record_format dspace
spelling sg-ntu-dr.10356-1514552021-06-24T04:12:18Z An optical neural chip for implementing complex-valued neural network Zhang, Hui Gu, Mile Jiang, Xudong Thompson, Jayne Cai, Hong Paesani‬‪, Stefano Santagati, ‪Raffaele Laing, ‪Anthony Zhang, Yi Yung, Man Hong Shi, Yuzhi Muhammad Faeyz Karim Lo, Guo Qiang Luo, Xian Shu Dong, Bin Kwong, Dim Lee Kwek, Leong Chuan Liu, Ai Qun School of Electrical and Electronic Engineering Engineering Integrated Optics Photonic Devices Complex-valued neural networks have many advantages over their real-valued counterparts. Conventional digital electronic computing platforms are incapable of executing truly complex-valued representations and operations. In contrast, optical computing platforms that encode information in both phase and magnitude can execute complex arithmetic by optical interference, offering significantly enhanced computational speed and energy efficiency. However, to date, most demonstrations of optical neural networks still only utilize conventional real-valued frameworks that are designed for digital computers, forfeiting many of the advantages of optical computing such as efficient complex-valued operations. In this article, we highlight an optical neural chip (ONC) that implements truly complex-valued neural networks. We benchmark the performance of our complex-valued ONC in four settings: simple Boolean tasks, species classification of an Iris dataset, classifying nonlinear datasets (Circle and Spiral), and handwriting recognition. Strong learning capabilities (i.e., high accuracy, fast convergence and the capability to construct nonlinear decision boundaries) are achieved by our complex-valued ONC compared to its real-valued counterpart. Ministry of Education (MOE) National Research Foundation (NRF) Published version 2021-06-24T04:12:17Z 2021-06-24T04:12:17Z 2021 Journal Article Zhang, H., Gu, M., Jiang, X., Thompson, J., Cai, H., Paesani‬‪, S., Santagati, ‪., Laing, ‪., Zhang, Y., Yung, M. H., Shi, Y., Muhammad Faeyz Karim, Lo, G. Q., Luo, X. S., Dong, B., Kwong, D. L., Kwek, L. C. & Liu, A. Q. (2021). An optical neural chip for implementing complex-valued neural network. Nature Communications, 12(457). https://dx.doi.org/10.1038/s41467-020-20719-7 2041-1723 https://hdl.handle.net/10356/151455 10.1038/s41467-020-20719-7 457 12 en Nature Communications © 2021 The Author(s). This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering
Integrated Optics
Photonic Devices
spellingShingle Engineering
Integrated Optics
Photonic Devices
Zhang, Hui
Gu, Mile
Jiang, Xudong
Thompson, Jayne
Cai, Hong
Paesani‬‪, Stefano
Santagati, ‪Raffaele
Laing, ‪Anthony
Zhang, Yi
Yung, Man Hong
Shi, Yuzhi
Muhammad Faeyz Karim
Lo, Guo Qiang
Luo, Xian Shu
Dong, Bin
Kwong, Dim Lee
Kwek, Leong Chuan
Liu, Ai Qun
An optical neural chip for implementing complex-valued neural network
description Complex-valued neural networks have many advantages over their real-valued counterparts. Conventional digital electronic computing platforms are incapable of executing truly complex-valued representations and operations. In contrast, optical computing platforms that encode information in both phase and magnitude can execute complex arithmetic by optical interference, offering significantly enhanced computational speed and energy efficiency. However, to date, most demonstrations of optical neural networks still only utilize conventional real-valued frameworks that are designed for digital computers, forfeiting many of the advantages of optical computing such as efficient complex-valued operations. In this article, we highlight an optical neural chip (ONC) that implements truly complex-valued neural networks. We benchmark the performance of our complex-valued ONC in four settings: simple Boolean tasks, species classification of an Iris dataset, classifying nonlinear datasets (Circle and Spiral), and handwriting recognition. Strong learning capabilities (i.e., high accuracy, fast convergence and the capability to construct nonlinear decision boundaries) are achieved by our complex-valued ONC compared to its real-valued counterpart.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Zhang, Hui
Gu, Mile
Jiang, Xudong
Thompson, Jayne
Cai, Hong
Paesani‬‪, Stefano
Santagati, ‪Raffaele
Laing, ‪Anthony
Zhang, Yi
Yung, Man Hong
Shi, Yuzhi
Muhammad Faeyz Karim
Lo, Guo Qiang
Luo, Xian Shu
Dong, Bin
Kwong, Dim Lee
Kwek, Leong Chuan
Liu, Ai Qun
format Article
author Zhang, Hui
Gu, Mile
Jiang, Xudong
Thompson, Jayne
Cai, Hong
Paesani‬‪, Stefano
Santagati, ‪Raffaele
Laing, ‪Anthony
Zhang, Yi
Yung, Man Hong
Shi, Yuzhi
Muhammad Faeyz Karim
Lo, Guo Qiang
Luo, Xian Shu
Dong, Bin
Kwong, Dim Lee
Kwek, Leong Chuan
Liu, Ai Qun
author_sort Zhang, Hui
title An optical neural chip for implementing complex-valued neural network
title_short An optical neural chip for implementing complex-valued neural network
title_full An optical neural chip for implementing complex-valued neural network
title_fullStr An optical neural chip for implementing complex-valued neural network
title_full_unstemmed An optical neural chip for implementing complex-valued neural network
title_sort optical neural chip for implementing complex-valued neural network
publishDate 2021
url https://hdl.handle.net/10356/151455
_version_ 1703971172883890176