时域神经处理的面积效率倍增累积架构与实现

2021 International Conference on Field-Programmable Technology (ICFPT) Pub Date : 2021-12-06 DOI:10.1109/ICFPT52863.2021.9609809

Ichiro Kawashima, Yuichi Katori, T. Morie, H. Tamukoh

{"title":"时域神经处理的面积效率倍增累积架构与实现","authors":"Ichiro Kawashima, Yuichi Katori, T. Morie, H. Tamukoh","doi":"10.1109/ICFPT52863.2021.9609809","DOIUrl":null,"url":null,"abstract":"In our work, a new area-efficient multiply-accumulation scheme for time-domain neural processing named differential multiply-accumulation is proposed. Our new scheme reduces hardware resources utilization of multiply-accumulation with suppressing the increasing computational time resulting from the time-multiplexing. As a result, 2,048 neurons of fully connected CBM and RC-CBM were synthesized for a single field-programmable gate array (FPGA).","PeriodicalId":376220,"journal":{"name":"2021 International Conference on Field-Programmable Technology (ICFPT)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"An area-efficient multiply-accumulation architecture and implementations for time-domain neural processing\",\"authors\":\"Ichiro Kawashima, Yuichi Katori, T. Morie, H. Tamukoh\",\"doi\":\"10.1109/ICFPT52863.2021.9609809\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In our work, a new area-efficient multiply-accumulation scheme for time-domain neural processing named differential multiply-accumulation is proposed. Our new scheme reduces hardware resources utilization of multiply-accumulation with suppressing the increasing computational time resulting from the time-multiplexing. As a result, 2,048 neurons of fully connected CBM and RC-CBM were synthesized for a single field-programmable gate array (FPGA).\",\"PeriodicalId\":376220,\"journal\":{\"name\":\"2021 International Conference on Field-Programmable Technology (ICFPT)\",\"volume\":\"45 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-12-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 International Conference on Field-Programmable Technology (ICFPT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICFPT52863.2021.9609809\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on Field-Programmable Technology (ICFPT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICFPT52863.2021.9609809","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

摘要

在我们的工作中，提出了一种新的时域神经处理的面积高效的乘法-积累方案，称为微分乘法-积累。新方案通过抑制时间复用带来的计算时间的增加，降低了乘法累加的硬件资源利用率。结果表明，在单个现场可编程门阵列(FPGA)上合成了2,048个全连接CBM和RC-CBM神经元。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

An area-efficient multiply-accumulation architecture and implementations for time-domain neural processing

In our work, a new area-efficient multiply-accumulation scheme for time-domain neural processing named differential multiply-accumulation is proposed. Our new scheme reduces hardware resources utilization of multiply-accumulation with suppressing the increasing computational time resulting from the time-multiplexing. As a result, 2,048 neurons of fully connected CBM and RC-CBM were synthesized for a single field-programmable gate array (FPGA).

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2021 International Conference on Field-Programmable Technology (ICFPT)

自引率

0.00%

发文量