用Labview和Matlab编写的正弦函数对称表加法前馈神经网络

Q4 Computer Science

International Journal of Computer Science and Applications Pub Date : 2014-04-30 DOI:10.5121/IJCSA.2014.4201

Fadhil A. Ali

{"title":"用Labview和Matlab编写的正弦函数对称表加法前馈神经网络","authors":"Fadhil A. Ali","doi":"10.5121/IJCSA.2014.4201","DOIUrl":null,"url":null,"abstract":"This work is proposed thefeed forward neural network with symmetric table addition methodto design the neuron synapses algorithm of the sine function approximations, and according to theTaylor series expansion. Matlab code and LabVIEW are used to build and create the neural network , which has been designed and traineddatabase set to improve its performance, and gets the besta global convergence with small value of MSE errors and 97.22% accuracy.","PeriodicalId":39465,"journal":{"name":"International Journal of Computer Science and Applications","volume":"75 1","pages":"1-12"},"PeriodicalIF":0.0000,"publicationDate":"2014-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Feed Forward Neural Network For Sine Function With Symmetric Table Addition Method Using Labview And Matlab Code\",\"authors\":\"Fadhil A. Ali\",\"doi\":\"10.5121/IJCSA.2014.4201\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This work is proposed thefeed forward neural network with symmetric table addition methodto design the neuron synapses algorithm of the sine function approximations, and according to theTaylor series expansion. Matlab code and LabVIEW are used to build and create the neural network , which has been designed and traineddatabase set to improve its performance, and gets the besta global convergence with small value of MSE errors and 97.22% accuracy.\",\"PeriodicalId\":39465,\"journal\":{\"name\":\"International Journal of Computer Science and Applications\",\"volume\":\"75 1\",\"pages\":\"1-12\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2014-04-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Computer Science and Applications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.5121/IJCSA.2014.4201\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"Computer Science\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Computer Science and Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5121/IJCSA.2014.4201","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Computer Science","Score":null,"Total":0}

引用次数: 1

摘要

本工作提出了前馈神经网络用对称表加法法设计神经元突触的正弦函数逼近算法，并根据泰勒级数展开。利用Matlab代码和LabVIEW构建和创建神经网络，设计并训练了数据库集，提高了神经网络的性能，得到了最佳的全局收敛性，MSE误差值较小，准确率为97.22%。

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

Feed Forward Neural Network For Sine Function With Symmetric Table Addition Method Using Labview And Matlab Code

This work is proposed thefeed forward neural network with symmetric table addition methodto design the neuron synapses algorithm of the sine function approximations, and according to theTaylor series expansion. Matlab code and LabVIEW are used to build and create the neural network , which has been designed and traineddatabase set to improve its performance, and gets the besta global convergence with small value of MSE errors and 97.22% accuracy.

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

International Journal of Computer Science and Applications Computer Science-Computer Science Applications

自引率

0.00%

发文量

期刊介绍： IJCSA is an international forum for scientists and engineers involved in computer science and its applications to publish high quality and refereed papers. Papers reporting original research and innovative applications from all parts of the world are welcome. Papers for publication in the IJCSA are selected through rigorous peer review to ensure originality, timeliness, relevance, and readability.