Space-efficient optical computing with an integrated chip diffractive neural network
Large-scale, highly integrated and low-power-consuming hardware is becoming progressively more important for realizing optical neural networks (ONNs) capable of advanced optical computing. Traditional experimental implementations need N2 units such as Mach-Zehnder interferometers (MZIs) for an input...
Saved in:
Main Authors: | , , , , , , , , , , , , , , , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/160409 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-160409 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1604092023-02-28T20:01:23Z Space-efficient optical computing with an integrated chip diffractive neural network Zhu, Hanhan Zou, Jun Zhang, Hengyi Shi, Yuzhi Luo, Shibo Wang, N. Cai, H. Wan, Liangxia Wang, Bo Jiang, Xudong Thompson, Jayne Luo, Xianshu Zhou, Xuanhe Xiao, Limin Huang, W. Patrick, Lento Gu, Mile Kwek, Leong Chuan Liu, Ai Qun School of Physical and Mathematical Sciences Quantum Science and Engineering Centre Quantum Hub Science::Physics Artificial Intelligence Computers Large-scale, highly integrated and low-power-consuming hardware is becoming progressively more important for realizing optical neural networks (ONNs) capable of advanced optical computing. Traditional experimental implementations need N2 units such as Mach-Zehnder interferometers (MZIs) for an input dimension N to realize typical computing operations (convolutions and matrix multiplication), resulting in limited scalability and consuming excessive power. Here, we propose the integrated diffractive optical network for implementing parallel Fourier transforms, convolution operations and application-specific optical computing using two ultracompact diffractive cells (Fourier transform operation) and only N MZIs. The footprint and energy consumption scales linearly with the input data dimension, instead of the quadratic scaling in the traditional ONN framework. A ~10-fold reduction in both footprint and energy consumption, as well as equal high accuracy with previous MZI-based ONNs was experimentally achieved for computations performed on the MNIST and Fashion-MNIST datasets. The integrated diffractive optical network (IDNN) chip demonstrates a promising avenue towards scalable and low-power-consumption optical computational chips for optical-artificial-intelligence. Ministry of Education (MOE) National Research Foundation (NRF) Published version This work was supported by the Singapore National Research Foundation under the Competitive Research Program (NRFCRP13-2014-01) and the Singapore Ministry of Education (MOE) Tier 3 grant (MOE2017-T3-1-001). 2022-07-21T06:09:30Z 2022-07-21T06:09:30Z 2022 Journal Article Zhu, H., Zou, J., Zhang, H., Shi, Y., Luo, S., Wang, N., Cai, H., Wan, L., Wang, B., Jiang, X., Thompson, J., Luo, X., Zhou, X., Xiao, L., Huang, W., Patrick, L., Gu, M., Kwek, L. C. & Liu, A. Q. (2022). Space-efficient optical computing with an integrated chip diffractive neural network. Nature Communications, 13(1), 1044-. https://dx.doi.org/10.1038/s41467-022-28702-0 2041-1723 https://hdl.handle.net/10356/160409 10.1038/s41467-022-28702-0 35210432 2-s2.0-85125348441 1 13 1044 en NRFCRP13-2014-01 MOE2017-T3-1-001 Nature Communications © 2022 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 |
Science::Physics Artificial Intelligence Computers |
spellingShingle |
Science::Physics Artificial Intelligence Computers Zhu, Hanhan Zou, Jun Zhang, Hengyi Shi, Yuzhi Luo, Shibo Wang, N. Cai, H. Wan, Liangxia Wang, Bo Jiang, Xudong Thompson, Jayne Luo, Xianshu Zhou, Xuanhe Xiao, Limin Huang, W. Patrick, Lento Gu, Mile Kwek, Leong Chuan Liu, Ai Qun Space-efficient optical computing with an integrated chip diffractive neural network |
description |
Large-scale, highly integrated and low-power-consuming hardware is becoming progressively more important for realizing optical neural networks (ONNs) capable of advanced optical computing. Traditional experimental implementations need N2 units such as Mach-Zehnder interferometers (MZIs) for an input dimension N to realize typical computing operations (convolutions and matrix multiplication), resulting in limited scalability and consuming excessive power. Here, we propose the integrated diffractive optical network for implementing parallel Fourier transforms, convolution operations and application-specific optical computing using two ultracompact diffractive cells (Fourier transform operation) and only N MZIs. The footprint and energy consumption scales linearly with the input data dimension, instead of the quadratic scaling in the traditional ONN framework. A ~10-fold reduction in both footprint and energy consumption, as well as equal high accuracy with previous MZI-based ONNs was experimentally achieved for computations performed on the MNIST and Fashion-MNIST datasets. The integrated diffractive optical network (IDNN) chip demonstrates a promising avenue towards scalable and low-power-consumption optical computational chips for optical-artificial-intelligence. |
author2 |
School of Physical and Mathematical Sciences |
author_facet |
School of Physical and Mathematical Sciences Zhu, Hanhan Zou, Jun Zhang, Hengyi Shi, Yuzhi Luo, Shibo Wang, N. Cai, H. Wan, Liangxia Wang, Bo Jiang, Xudong Thompson, Jayne Luo, Xianshu Zhou, Xuanhe Xiao, Limin Huang, W. Patrick, Lento Gu, Mile Kwek, Leong Chuan Liu, Ai Qun |
format |
Article |
author |
Zhu, Hanhan Zou, Jun Zhang, Hengyi Shi, Yuzhi Luo, Shibo Wang, N. Cai, H. Wan, Liangxia Wang, Bo Jiang, Xudong Thompson, Jayne Luo, Xianshu Zhou, Xuanhe Xiao, Limin Huang, W. Patrick, Lento Gu, Mile Kwek, Leong Chuan Liu, Ai Qun |
author_sort |
Zhu, Hanhan |
title |
Space-efficient optical computing with an integrated chip diffractive neural network |
title_short |
Space-efficient optical computing with an integrated chip diffractive neural network |
title_full |
Space-efficient optical computing with an integrated chip diffractive neural network |
title_fullStr |
Space-efficient optical computing with an integrated chip diffractive neural network |
title_full_unstemmed |
Space-efficient optical computing with an integrated chip diffractive neural network |
title_sort |
space-efficient optical computing with an integrated chip diffractive neural network |
publishDate |
2022 |
url |
https://hdl.handle.net/10356/160409 |
_version_ |
1759855610410565632 |