Optoelectronic Chip for the Implementation of Back Error Propagation

H. Li, J. Drolet, D. Psaltis, M. Handschy
{"title":"Optoelectronic Chip for the Implementation of Back Error Propagation","authors":"H. Li, J. Drolet, D. Psaltis, M. Handschy","doi":"10.1109/LEOSST.1992.697512","DOIUrl":null,"url":null,"abstract":"We present a CMOS silicon chip that optically implements the back error propagation (BEP) algorithm [1] of a two layer neural network. The chip has eight units (or \"neurons\") on a area of approximately 2x2 mm. Each unit consists of a phototransistor as the detector, a modulator pad for light modulation, sample-and-hold circuits, and additional circuits necessary to perform the BEP algorithm.","PeriodicalId":355341,"journal":{"name":"Summer Topical Meeting Digest on Broadband Analog and Digital Optoelectronics, Optical Multiple Access Networks, Integrated Optoelectronics, Smart Pixels","volume":"61 4 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1992-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Summer Topical Meeting Digest on Broadband Analog and Digital Optoelectronics, Optical Multiple Access Networks, Integrated Optoelectronics, Smart Pixels","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/LEOSST.1992.697512","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

We present a CMOS silicon chip that optically implements the back error propagation (BEP) algorithm [1] of a two layer neural network. The chip has eight units (or "neurons") on a area of approximately 2x2 mm. Each unit consists of a phototransistor as the detector, a modulator pad for light modulation, sample-and-hold circuits, and additional circuits necessary to perform the BEP algorithm.
实现反向误差传播的光电芯片
我们提出了一种CMOS硅片,光学实现了两层神经网络的反向误差传播(BEP)算法[1]。该芯片在大约2x2毫米的面积上有8个单元(或“神经元”)。每个单元由作为检测器的光电晶体管、用于光调制的调制器衬垫、采样保持电路以及执行BEP算法所需的附加电路组成。
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 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信