内存模拟计算中减小权值变化的接口控制提高识别精度

2022 IEEE International Memory Workshop (IMW) Pub Date : 2022-05-01 DOI:10.1109/IMW52921.2022.9779296

S. Park, Gyonhui Lee, Youngjae Kwon, D. Suh, Hanwool Lee, Sangeun Je, Dabin Kim, Dohan Lee, Seungwook Ryu, Seungbum Kim, Euiseok Kim, Sunghoon Lee, Kyoung Park, Seho Lee, Myung-Hee Na, Seonyong Cha

{"title":"内存模拟计算中减小权值变化的接口控制提高识别精度","authors":"S. Park, Gyonhui Lee, Youngjae Kwon, D. Suh, Hanwool Lee, Sangeun Je, Dabin Kim, Dohan Lee, Seungwook Ryu, Seungbum Kim, Euiseok Kim, Sunghoon Lee, Kyoung Park, Seho Lee, Myung-Hee Na, Seonyong Cha","doi":"10.1109/IMW52921.2022.9779296","DOIUrl":null,"url":null,"abstract":"As AI technology develops, it is necessary to verify the technical feasibility of Memory-Centric convergence technology. Previously investigated resistive synaptic devices (RSDs) can successfully mimic the function of biological synapses. However, the effect of the system recognition rate reflecting the variation of 16 weight states has not been studied yet. In this article, we perform simulations of various weight variation sets through real resistive synaptic device (RSD) engineering in Analog Computation-in-Memory (ACiM) system. These simulation results can provide guidelines for the continued design and optimization of a resistive synaptic device for realizing ACiM.","PeriodicalId":132074,"journal":{"name":"2022 IEEE International Memory Workshop (IMW)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Recognition Accuracy Enhancement using Interface Control with Weight Variation-Lowering in Analog Computation-in-Memory\",\"authors\":\"S. Park, Gyonhui Lee, Youngjae Kwon, D. Suh, Hanwool Lee, Sangeun Je, Dabin Kim, Dohan Lee, Seungwook Ryu, Seungbum Kim, Euiseok Kim, Sunghoon Lee, Kyoung Park, Seho Lee, Myung-Hee Na, Seonyong Cha\",\"doi\":\"10.1109/IMW52921.2022.9779296\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"As AI technology develops, it is necessary to verify the technical feasibility of Memory-Centric convergence technology. Previously investigated resistive synaptic devices (RSDs) can successfully mimic the function of biological synapses. However, the effect of the system recognition rate reflecting the variation of 16 weight states has not been studied yet. In this article, we perform simulations of various weight variation sets through real resistive synaptic device (RSD) engineering in Analog Computation-in-Memory (ACiM) system. These simulation results can provide guidelines for the continued design and optimization of a resistive synaptic device for realizing ACiM.\",\"PeriodicalId\":132074,\"journal\":{\"name\":\"2022 IEEE International Memory Workshop (IMW)\",\"volume\":\"27 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 IEEE International Memory Workshop (IMW)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IMW52921.2022.9779296\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE International Memory Workshop (IMW)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IMW52921.2022.9779296","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

随着人工智能技术的发展，有必要验证以内存为中心的融合技术的技术可行性。先前研究的电阻性突触装置(rsd)可以成功地模拟生物突触的功能。然而，反映16种权值状态变化的系统识别率的影响尚未得到研究。在本文中，我们通过在模拟内存计算(ACiM)系统中的真实电阻突触装置(RSD)工程进行了各种权重变化集的模拟。这些仿真结果可以为实现ACiM的电阻性突触装置的进一步设计和优化提供指导。

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

Recognition Accuracy Enhancement using Interface Control with Weight Variation-Lowering in Analog Computation-in-Memory

As AI technology develops, it is necessary to verify the technical feasibility of Memory-Centric convergence technology. Previously investigated resistive synaptic devices (RSDs) can successfully mimic the function of biological synapses. However, the effect of the system recognition rate reflecting the variation of 16 weight states has not been studied yet. In this article, we perform simulations of various weight variation sets through real resistive synaptic device (RSD) engineering in Analog Computation-in-Memory (ACiM) system. These simulation results can provide guidelines for the continued design and optimization of a resistive synaptic device for realizing ACiM.

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

2022 IEEE International Memory Workshop (IMW)

自引率

0.00%

发文量