多层神经网络中硬件突触权的模拟忆阻特性研究

IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS

Advanced intelligent systems (Weinheim an der Bergstrasse, Germany) Pub Date : 2025-03-16 DOI:10.1002/aisy.202570012

Jingon Jang, Yoonseok Song, Sungjun Park

{"title":"多层神经网络中硬件突触权的模拟忆阻特性研究","authors":"Jingon Jang, Yoonseok Song, Sungjun Park","doi":"10.1002/aisy.202570012","DOIUrl":null,"url":null,"abstract":"<p><b>Analog Memristor Characteristics</b>\n </p><p>The systematic design of memristor-based neural network is provided by analog conductance state parameters to accurately emulate the software-based high-resolution weight at discrete device level. The requirement of discrete analog conductance of memristor device is measured as ≈50 states with nonlinearity value of ≈0.142 within the deviation range of 5% for inference accuracy of ≈84.36% and loss value of ≈0.168. Further details can be found in article number 2400710 by Jingon Jang, Yoonseok Song, and Sungjun Park.\n <figure>\n <div><picture>\n <source></source></picture><p></p>\n </div>\n </figure></p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":"7 3","pages":""},"PeriodicalIF":6.8000,"publicationDate":"2025-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202570012","citationCount":"0","resultStr":"{\"title\":\"Investigation of Analog Memristor Characteristics for Hardware Synaptic Weight in Multilayer Neural Network\",\"authors\":\"Jingon Jang, Yoonseok Song, Sungjun Park\",\"doi\":\"10.1002/aisy.202570012\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><b>Analog Memristor Characteristics</b>\\n </p><p>The systematic design of memristor-based neural network is provided by analog conductance state parameters to accurately emulate the software-based high-resolution weight at discrete device level. The requirement of discrete analog conductance of memristor device is measured as ≈50 states with nonlinearity value of ≈0.142 within the deviation range of 5% for inference accuracy of ≈84.36% and loss value of ≈0.168. Further details can be found in article number 2400710 by Jingon Jang, Yoonseok Song, and Sungjun Park.\\n <figure>\\n <div><picture>\\n <source></source></picture><p></p>\\n </div>\\n </figure></p>\",\"PeriodicalId\":93858,\"journal\":{\"name\":\"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)\",\"volume\":\"7 3\",\"pages\":\"\"},\"PeriodicalIF\":6.8000,\"publicationDate\":\"2025-03-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202570012\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/aisy.202570012\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AUTOMATION & CONTROL SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","FirstCategoryId":"1085","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/aisy.202570012","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}

引用次数: 0

摘要

通过模拟电导状态参数，提供基于忆阻器的神经网络系统设计，在离散器件级精确模拟基于软件的高分辨率权重。测量忆阻器器件离散模拟电导的要求为≈50个状态，在5%的偏差范围内，非线性值为≈0.142，推理精度为≈84.36%，损耗值为≈0.168。详细内容请参见《2400710号文章》（张景根、宋允锡、朴成俊）。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

Investigation of Analog Memristor Characteristics for Hardware Synaptic Weight in Multilayer Neural Network

查看原文本刊更多论文

Investigation of Analog Memristor Characteristics for Hardware Synaptic Weight in Multilayer Neural Network

Analog Memristor Characteristics

The systematic design of memristor-based neural network is provided by analog conductance state parameters to accurately emulate the software-based high-resolution weight at discrete device level. The requirement of discrete analog conductance of memristor device is measured as ≈50 states with nonlinearity value of ≈0.142 within the deviation range of 5% for inference accuracy of ≈84.36% and loss value of ≈0.168. Further details can be found in article number 2400710 by Jingon Jang, Yoonseok Song, and Sungjun Park.

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

Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)

CiteScore

1.30

自引率

0.00%

发文量

审稿时长

4 weeks