前馈神经网络的FPGA优化实现

2008 11th International Conference on Optimization of Electrical and Electronic Equipment Pub Date : 2008-05-22 DOI:10.1109/OPTIM.2008.4602494

S. Oniga, A. Tisan, D. Mic, A. Buchman, A. Vida-Ratiu

{"title":"前馈神经网络的FPGA优化实现","authors":"S. Oniga, A. Tisan, D. Mic, A. Buchman, A. Vida-Ratiu","doi":"10.1109/OPTIM.2008.4602494","DOIUrl":null,"url":null,"abstract":"This paper presents an in depth study of FPGA implementation of feed-forward neural networks regarding error reduction as a function of number of bits used for weights representation. Xilinx block parameters influence on resources occupied by network and the maximum working frequency is also studied.","PeriodicalId":244464,"journal":{"name":"2008 11th International Conference on Optimization of Electrical and Electronic Equipment","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2008-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"18","resultStr":"{\"title\":\"Optimizing FPGA implementation of Feed-Forward Neural Networks\",\"authors\":\"S. Oniga, A. Tisan, D. Mic, A. Buchman, A. Vida-Ratiu\",\"doi\":\"10.1109/OPTIM.2008.4602494\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents an in depth study of FPGA implementation of feed-forward neural networks regarding error reduction as a function of number of bits used for weights representation. Xilinx block parameters influence on resources occupied by network and the maximum working frequency is also studied.\",\"PeriodicalId\":244464,\"journal\":{\"name\":\"2008 11th International Conference on Optimization of Electrical and Electronic Equipment\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2008-05-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"18\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2008 11th International Conference on Optimization of Electrical and Electronic Equipment\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/OPTIM.2008.4602494\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2008 11th International Conference on Optimization of Electrical and Electronic Equipment","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/OPTIM.2008.4602494","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 18

摘要

本文对前馈神经网络的FPGA实现进行了深入的研究，将误差降低作为用于权重表示的比特数的函数。研究了Xilinx块参数对网络资源占用和最大工作频率的影响。

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

Optimizing FPGA implementation of Feed-Forward Neural Networks

This paper presents an in depth study of FPGA implementation of feed-forward neural networks regarding error reduction as a function of number of bits used for weights representation. Xilinx block parameters influence on resources occupied by network and the maximum working frequency is also studied.

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

2008 11th International Conference on Optimization of Electrical and Electronic Equipment

自引率

0.00%

发文量