神经网络投票的实现方法

2004 IEEE International Conference onComputational Intelligence for Measurement Systems and Applications, 2004. CIMSA. Pub Date : 2004-07-14 DOI:10.1109/CIMSA.2004.1397240

Huang Qian, Zheng Qilun, Fan Wenhao

{"title":"神经网络投票的实现方法","authors":"Huang Qian, Zheng Qilun, Fan Wenhao","doi":"10.1109/CIMSA.2004.1397240","DOIUrl":null,"url":null,"abstract":"In this paper, four types of voting schemes generally adopted in competition neural networks has been compared in their rationality, integrity and maneuverability. A novel hardware design approach especially for the most advanced Nash voting scheme is presented. The proposed method simplifies the circuit construction by changing multiplication operations into logarithm operations. The circuit is experimentally measured with PSPICE.","PeriodicalId":102405,"journal":{"name":"2004 IEEE International Conference onComputational Intelligence for Measurement Systems and Applications, 2004. CIMSA.","volume":"80 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2004-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Implementation method for voting of neural networks\",\"authors\":\"Huang Qian, Zheng Qilun, Fan Wenhao\",\"doi\":\"10.1109/CIMSA.2004.1397240\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, four types of voting schemes generally adopted in competition neural networks has been compared in their rationality, integrity and maneuverability. A novel hardware design approach especially for the most advanced Nash voting scheme is presented. The proposed method simplifies the circuit construction by changing multiplication operations into logarithm operations. The circuit is experimentally measured with PSPICE.\",\"PeriodicalId\":102405,\"journal\":{\"name\":\"2004 IEEE International Conference onComputational Intelligence for Measurement Systems and Applications, 2004. CIMSA.\",\"volume\":\"80 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2004-07-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2004 IEEE International Conference onComputational Intelligence for Measurement Systems and Applications, 2004. CIMSA.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CIMSA.2004.1397240\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2004 IEEE International Conference onComputational Intelligence for Measurement Systems and Applications, 2004. CIMSA.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CIMSA.2004.1397240","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

本文比较了竞争神经网络中常用的四种投票方案的合理性、完整性和可操作性。针对最先进的纳什投票方案，提出了一种新颖的硬件设计方法。该方法将乘法运算改为对数运算，简化了电路结构。用PSPICE对电路进行了实验测量。

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

Implementation method for voting of neural networks

In this paper, four types of voting schemes generally adopted in competition neural networks has been compared in their rationality, integrity and maneuverability. A novel hardware design approach especially for the most advanced Nash voting scheme is presented. The proposed method simplifies the circuit construction by changing multiplication operations into logarithm operations. The circuit is experimentally measured with PSPICE.

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

2004 IEEE International Conference onComputational Intelligence for Measurement Systems and Applications, 2004. CIMSA.

自引率

0.00%

发文量