{"title":"用于人工神经网络的可编程向量矩阵乘法器","authors":"F. Kub, I. Mack, K. Moon","doi":"10.1109/VLSIC.1989.1037507","DOIUrl":null,"url":null,"abstract":"For the hyblid digital-analog approach, rhom in Figure 1. the --log loultiplier w e i g h t valves are generated from digical words stored in digital memory. The analog voltages are X-Y addrossed to rhe nulciplier sites using decoding circuitry and are dynsmically stored on capaciCorr aL the gatel of WOSFET conductance elements. The analog voltages are periodicelly refreshed from rhe vsighr values stored in the digital memory.","PeriodicalId":136228,"journal":{"name":"Symposium 1989 on VLSI Circuits","volume":"26 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1989-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"Programmable vector-matrix multipliers for artificial neural networks\",\"authors\":\"F. Kub, I. Mack, K. Moon\",\"doi\":\"10.1109/VLSIC.1989.1037507\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"For the hyblid digital-analog approach, rhom in Figure 1. the --log loultiplier w e i g h t valves are generated from digical words stored in digital memory. The analog voltages are X-Y addrossed to rhe nulciplier sites using decoding circuitry and are dynsmically stored on capaciCorr aL the gatel of WOSFET conductance elements. The analog voltages are periodicelly refreshed from rhe vsighr values stored in the digital memory.\",\"PeriodicalId\":136228,\"journal\":{\"name\":\"Symposium 1989 on VLSI Circuits\",\"volume\":\"26 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1989-05-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Symposium 1989 on VLSI Circuits\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/VLSIC.1989.1037507\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Symposium 1989 on VLSI Circuits","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/VLSIC.1989.1037507","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Programmable vector-matrix multipliers for artificial neural networks
For the hyblid digital-analog approach, rhom in Figure 1. the --log loultiplier w e i g h t valves are generated from digical words stored in digital memory. The analog voltages are X-Y addrossed to rhe nulciplier sites using decoding circuitry and are dynsmically stored on capaciCorr aL the gatel of WOSFET conductance elements. The analog voltages are periodicelly refreshed from rhe vsighr values stored in the digital memory.