Mixed precision quantization of silicon optical neural network chip

IF 2.2 3区 物理与天体物理 Q2 OPTICS Optics Communications Pub Date : 2024-10-23 DOI:10.1016/j.optcom.2024.131231
Ye Zhang , Ruiting Wang , Yejin Zhang , Jiaoqing Pan
{"title":"Mixed precision quantization of silicon optical neural network chip","authors":"Ye Zhang ,&nbsp;Ruiting Wang ,&nbsp;Yejin Zhang ,&nbsp;Jiaoqing Pan","doi":"10.1016/j.optcom.2024.131231","DOIUrl":null,"url":null,"abstract":"<div><div>In recent years, the field of neural network research has witnessed remarkable advancements in various domains. One of the emerging approaches is the integration of photonic computing, which leverages the unique properties of light for ultra-fast information processing. In this article, we establish a mixed precision quantization model to silicon-based optical neural networks and evaluates their performance on the MNIST and Fashion-MNIST datasets. Through a genetic algorithm-based optimization process, we achieve significant parameter compression while maintaining competitive accuracy. Our findings demonstrate that with an average quantization bitwidth of 4.5 bits on the MNIST dataset, we achieve an impressive 85.94% reduction in parameter size compared to traditional 32-bit networks, with only a marginal accuracy drop of 0.65%. Similarly, on the Fashion-MNIST dataset, we achieve an average quantization bitwidth of 5.67 bits, resulting in an 82.28% reduction in parameter size with a slight accuracy drop of 0.8%.</div></div>","PeriodicalId":19586,"journal":{"name":"Optics Communications","volume":null,"pages":null},"PeriodicalIF":2.2000,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Optics Communications","FirstCategoryId":"101","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0030401824009684","RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"OPTICS","Score":null,"Total":0}
引用次数: 0

Abstract

In recent years, the field of neural network research has witnessed remarkable advancements in various domains. One of the emerging approaches is the integration of photonic computing, which leverages the unique properties of light for ultra-fast information processing. In this article, we establish a mixed precision quantization model to silicon-based optical neural networks and evaluates their performance on the MNIST and Fashion-MNIST datasets. Through a genetic algorithm-based optimization process, we achieve significant parameter compression while maintaining competitive accuracy. Our findings demonstrate that with an average quantization bitwidth of 4.5 bits on the MNIST dataset, we achieve an impressive 85.94% reduction in parameter size compared to traditional 32-bit networks, with only a marginal accuracy drop of 0.65%. Similarly, on the Fashion-MNIST dataset, we achieve an average quantization bitwidth of 5.67 bits, resulting in an 82.28% reduction in parameter size with a slight accuracy drop of 0.8%.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
硅光学神经网络芯片的混合精度量化
近年来,神经网络研究领域在各个领域都取得了显著进展。光子计算是新兴的方法之一,它利用光的独特特性进行超快信息处理。在本文中,我们为硅基光学神经网络建立了一个混合精度量化模型,并评估了它们在 MNIST 和 Fashion-MNIST 数据集上的性能。通过基于遗传算法的优化过程,我们实现了显著的参数压缩,同时保持了具有竞争力的精度。我们的研究结果表明,与传统的 32 位网络相比,在平均量化位宽为 4.5 位的 MNIST 数据集上,我们实现了令人印象深刻的 85.94% 的参数缩减,而准确率仅下降了 0.65%。同样,在时尚-MNIST 数据集上,我们实现了 5.67 比特的平均量化位宽,从而将参数大小减少了 82.28%,准确率却略微下降了 0.8%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Optics Communications
Optics Communications 物理-光学
CiteScore
5.10
自引率
8.30%
发文量
681
审稿时长
38 days
期刊介绍: Optics Communications invites original and timely contributions containing new results in various fields of optics and photonics. The journal considers theoretical and experimental research in areas ranging from the fundamental properties of light to technological applications. Topics covered include classical and quantum optics, optical physics and light-matter interactions, lasers, imaging, guided-wave optics and optical information processing. Manuscripts should offer clear evidence of novelty and significance. Papers concentrating on mathematical and computational issues, with limited connection to optics, are not suitable for publication in the Journal. Similarly, small technical advances, or papers concerned only with engineering applications or issues of materials science fall outside the journal scope.
期刊最新文献
Photonic physically unclonable functions using randomly positioned aluminum nanoholes Lamellar beam with similar propagation and imaging characteristics to a Bessel beam Toward a fast and non-darkroom solution for speckle correlation based scattering imaging An improvement of optical PPM communication with high security Terahertz refractive index control of 3D printing materials by UV exposure
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1