{"title":"一种新的深度神经网络随机乘法器","authors":"Subin Huh, Joonsang Yu, Kiyoung Choi","doi":"10.1109/ISOCC.2017.8368820","DOIUrl":null,"url":null,"abstract":"An XNOR gate is the most commonly used multiplier in bipolar encoded stochastic deep neural networks, but it is not suitable due to the inaccuracy in processing near-zero values. In this paper, we introduce a novel circuit that multiplies near-zero values more accurately and assess its performance with MNIST and CIFAR-10. For the CIFAR-10 dataset, the use of the proposed multipliers gives accuracy of 60.59%, improving by 11.64%p over the XNOR multiplier implementation.","PeriodicalId":248826,"journal":{"name":"2017 International SoC Design Conference (ISOCC)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A new stochastic mutiplier for deep neural networks\",\"authors\":\"Subin Huh, Joonsang Yu, Kiyoung Choi\",\"doi\":\"10.1109/ISOCC.2017.8368820\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"An XNOR gate is the most commonly used multiplier in bipolar encoded stochastic deep neural networks, but it is not suitable due to the inaccuracy in processing near-zero values. In this paper, we introduce a novel circuit that multiplies near-zero values more accurately and assess its performance with MNIST and CIFAR-10. For the CIFAR-10 dataset, the use of the proposed multipliers gives accuracy of 60.59%, improving by 11.64%p over the XNOR multiplier implementation.\",\"PeriodicalId\":248826,\"journal\":{\"name\":\"2017 International SoC Design Conference (ISOCC)\",\"volume\":\"80 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 International SoC Design Conference (ISOCC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISOCC.2017.8368820\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 International SoC Design Conference (ISOCC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISOCC.2017.8368820","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A new stochastic mutiplier for deep neural networks
An XNOR gate is the most commonly used multiplier in bipolar encoded stochastic deep neural networks, but it is not suitable due to the inaccuracy in processing near-zero values. In this paper, we introduce a novel circuit that multiplies near-zero values more accurately and assess its performance with MNIST and CIFAR-10. For the CIFAR-10 dataset, the use of the proposed multipliers gives accuracy of 60.59%, improving by 11.64%p over the XNOR multiplier implementation.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
