Please use this identifier to cite or link to this item:
Title: An optical neural chip for implementing complex-valued neural network
Authors: Zhang, H.
Gu, M. 
Jiang, X. D.
Thompson, J. 
Cai, H.
Paesani, S.
Santagati, R.
Laing, A.
Zhang, Y.
Yung, M. H.
Shi, Y. Z.
Muhammad, F. K.
Lo, G. Q.
Luo, X. S.
Dong, B.
Kwong, D. L.
Kwek, L. C. 
Liu, A. Q.
Issue Date: 19-Jan-2021
Publisher: Nature Research
Citation: Zhang, H., Gu, M., Jiang, X. D., Thompson, J., Cai, H., Paesani, S., Santagati, R., Laing, A., Zhang, Y., Yung, M. H., Shi, Y. Z., Muhammad, F. K., Lo, G. Q., Luo, X. S., Dong, B., Kwong, D. L., Kwek, L. C., Liu, A. Q. (2021-01-19). An optical neural chip for implementing complex-valued neural network. Nature Communications 12 (1) : 457. ScholarBank@NUS Repository.
Rights: Attribution 4.0 International
Abstract: 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. © 2021, The Author(s).
Source Title: Nature Communications
ISSN: 2041-1723
DOI: 10.1038/s41467-020-20719-7
Rights: Attribution 4.0 International
Appears in Collections:Elements
Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
10_1038_s41467-020-20719-7.pdf2.82 MBAdobe PDF




checked on Mar 18, 2023

Page view(s)

checked on Mar 16, 2023

Google ScholarTM



This item is licensed under a Creative Commons License Creative Commons