Performance of an optoelectronic neural network in the presence of noise

Optoelectronic neural networks must not only be highly parallel but also fast to compete with electrical systems. Receiver noise becomes an important consideration at high data rates; so the limits set by noise to network size and speed are analyzed. A network incorporating an array of high-speed mu...

Full description

Saved in:
Bibliographic Details
Published in:Applied optics (2004) 1995-08, Vol.34 (23), p.5230-5240
Main Author: Webb, R P
Format: Article
Language:English
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c288t-bd836e11a7c395b4e410aff2ebdeacee003b1d7342796a0302ad889543e4d8163
cites
container_end_page 5240
container_issue 23
container_start_page 5230
container_title Applied optics (2004)
container_volume 34
creator Webb, R P
description Optoelectronic neural networks must not only be highly parallel but also fast to compete with electrical systems. Receiver noise becomes an important consideration at high data rates; so the limits set by noise to network size and speed are analyzed. A network incorporating an array of high-speed multi-quantum-well modulators was constructed. It employed a general method for optical representation of bipolar values, which required only a minimal increase in network dimensions and gave the network immunity to common-mode parameter variations. Different ways of partitioning pattern-recognition problems were compared, and the accuracy of one configuration was tested with the experimental network over a range of noise levels.
doi_str_mv 10.1364/AO.34.005230
format article
fullrecord <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_proquest_miscellaneous_762686005</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>762686005</sourcerecordid><originalsourceid>FETCH-LOGICAL-c288t-bd836e11a7c395b4e410aff2ebdeacee003b1d7342796a0302ad889543e4d8163</originalsourceid><addsrcrecordid>eNo1kD1PwzAYhD2AaClszMgbU4K_7YxVBRSpUhlAYosc540IJHawEyH-PUGE6ZbnTneH0BUlOeVK3G6PORc5IZJxcoLWVMoio8y8rtB5Su-EcCkKfYZWjP4imqzR_gliE2JvvQMcGmw9DsMYoAM3xuBbhz1M0XazjF8hfuDW4_EN8BAhweLxoU1wgU4b2yW4XHSDXu7vnnf77HB8eNxtD5ljxoxZVRuugFKrHS9kJUBQYpuGQVWDdQBzx4rWmgumC2UJJ8zWxhRScBC1oYpv0M1f7hDD5wRpLPs2Oeg66yFMqdSKKaPmC2byeiGnqoe6HGLb2_hd_o_nP0UsWTU</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>762686005</pqid></control><display><type>article</type><title>Performance of an optoelectronic neural network in the presence of noise</title><source>Optica Publishing Group (OPG)</source><creator>Webb, R P</creator><creatorcontrib>Webb, R P</creatorcontrib><description>Optoelectronic neural networks must not only be highly parallel but also fast to compete with electrical systems. Receiver noise becomes an important consideration at high data rates; so the limits set by noise to network size and speed are analyzed. A network incorporating an array of high-speed multi-quantum-well modulators was constructed. It employed a general method for optical representation of bipolar values, which required only a minimal increase in network dimensions and gave the network immunity to common-mode parameter variations. Different ways of partitioning pattern-recognition problems were compared, and the accuracy of one configuration was tested with the experimental network over a range of noise levels.</description><identifier>ISSN: 1559-128X</identifier><identifier>DOI: 10.1364/AO.34.005230</identifier><identifier>PMID: 21052370</identifier><language>eng</language><publisher>United States</publisher><ispartof>Applied optics (2004), 1995-08, Vol.34 (23), p.5230-5240</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c288t-bd836e11a7c395b4e410aff2ebdeacee003b1d7342796a0302ad889543e4d8163</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,777,781,27905,27906</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/21052370$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Webb, R P</creatorcontrib><title>Performance of an optoelectronic neural network in the presence of noise</title><title>Applied optics (2004)</title><addtitle>Appl Opt</addtitle><description>Optoelectronic neural networks must not only be highly parallel but also fast to compete with electrical systems. Receiver noise becomes an important consideration at high data rates; so the limits set by noise to network size and speed are analyzed. A network incorporating an array of high-speed multi-quantum-well modulators was constructed. It employed a general method for optical representation of bipolar values, which required only a minimal increase in network dimensions and gave the network immunity to common-mode parameter variations. Different ways of partitioning pattern-recognition problems were compared, and the accuracy of one configuration was tested with the experimental network over a range of noise levels.</description><issn>1559-128X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1995</creationdate><recordtype>article</recordtype><recordid>eNo1kD1PwzAYhD2AaClszMgbU4K_7YxVBRSpUhlAYosc540IJHawEyH-PUGE6ZbnTneH0BUlOeVK3G6PORc5IZJxcoLWVMoio8y8rtB5Su-EcCkKfYZWjP4imqzR_gliE2JvvQMcGmw9DsMYoAM3xuBbhz1M0XazjF8hfuDW4_EN8BAhweLxoU1wgU4b2yW4XHSDXu7vnnf77HB8eNxtD5ljxoxZVRuugFKrHS9kJUBQYpuGQVWDdQBzx4rWmgumC2UJJ8zWxhRScBC1oYpv0M1f7hDD5wRpLPs2Oeg66yFMqdSKKaPmC2byeiGnqoe6HGLb2_hd_o_nP0UsWTU</recordid><startdate>19950810</startdate><enddate>19950810</enddate><creator>Webb, R P</creator><scope>NPM</scope><scope>7X8</scope></search><sort><creationdate>19950810</creationdate><title>Performance of an optoelectronic neural network in the presence of noise</title><author>Webb, R P</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c288t-bd836e11a7c395b4e410aff2ebdeacee003b1d7342796a0302ad889543e4d8163</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1995</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Webb, R P</creatorcontrib><collection>PubMed</collection><collection>MEDLINE - Academic</collection><jtitle>Applied optics (2004)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Webb, R P</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Performance of an optoelectronic neural network in the presence of noise</atitle><jtitle>Applied optics (2004)</jtitle><addtitle>Appl Opt</addtitle><date>1995-08-10</date><risdate>1995</risdate><volume>34</volume><issue>23</issue><spage>5230</spage><epage>5240</epage><pages>5230-5240</pages><issn>1559-128X</issn><abstract>Optoelectronic neural networks must not only be highly parallel but also fast to compete with electrical systems. Receiver noise becomes an important consideration at high data rates; so the limits set by noise to network size and speed are analyzed. A network incorporating an array of high-speed multi-quantum-well modulators was constructed. It employed a general method for optical representation of bipolar values, which required only a minimal increase in network dimensions and gave the network immunity to common-mode parameter variations. Different ways of partitioning pattern-recognition problems were compared, and the accuracy of one configuration was tested with the experimental network over a range of noise levels.</abstract><cop>United States</cop><pmid>21052370</pmid><doi>10.1364/AO.34.005230</doi><tpages>11</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1559-128X
ispartof Applied optics (2004), 1995-08, Vol.34 (23), p.5230-5240
issn 1559-128X
language eng
recordid cdi_proquest_miscellaneous_762686005
source Optica Publishing Group (OPG)
title Performance of an optoelectronic neural network in the presence of noise
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T05%3A19%3A00IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Performance%20of%20an%20optoelectronic%20neural%20network%20in%20the%20presence%20of%20noise&rft.jtitle=Applied%20optics%20(2004)&rft.au=Webb,%20R%20P&rft.date=1995-08-10&rft.volume=34&rft.issue=23&rft.spage=5230&rft.epage=5240&rft.pages=5230-5240&rft.issn=1559-128X&rft_id=info:doi/10.1364/AO.34.005230&rft_dat=%3Cproquest_pubme%3E762686005%3C/proquest_pubme%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c288t-bd836e11a7c395b4e410aff2ebdeacee003b1d7342796a0302ad889543e4d8163%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=762686005&rft_id=info:pmid/21052370&rfr_iscdi=true