R. Domínguez-Castro, Á. Rodríguez-Vázquez, S. Espejo, R. Carmona
{"title":"Four-quadrant one-transistor-synapse for high-density CNN implementations","authors":"R. Domínguez-Castro, Á. Rodríguez-Vázquez, S. Espejo, R. Carmona","doi":"10.1109/CNNA.1998.685377","DOIUrl":null,"url":null,"abstract":"Presents a linear four-quadrants, electrically-programmable, one-transistor synapse strategy applicable to the implementation of general massively-parallel analog processors in CMOS technology. It is specially suited for translationally-invariant processing arrays with local connectivity, and results in a significant reduction in area occupation and power dissipation of the basic processing units. This allows higher integration densities and therefore, permits the integration of larger arrays on a single chip.","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1998-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"23","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CNNA.1998.685377","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 23
Abstract
Presents a linear four-quadrants, electrically-programmable, one-transistor synapse strategy applicable to the implementation of general massively-parallel analog processors in CMOS technology. It is specially suited for translationally-invariant processing arrays with local connectivity, and results in a significant reduction in area occupation and power dissipation of the basic processing units. This allows higher integration densities and therefore, permits the integration of larger arrays on a single chip.