一种新的共轭梯度法训练前馈神经网络的性能评价

Q3 Mathematics

Mathematical Modeling and Computing Pub Date : 2023-01-01 DOI:10.23939/mmc2023.02.326

K. Kamilu, M. I. Sulaiman, A. Muhammad, A. W. Mohamad, M. Mamat

{"title":"一种新的共轭梯度法训练前馈神经网络的性能评价","authors":"K. Kamilu, M. I. Sulaiman, A. Muhammad, A. W. Mohamad, M. Mamat","doi":"10.23939/mmc2023.02.326","DOIUrl":null,"url":null,"abstract":"In this paper, we construct a new conjugate gradient method for solving unconstrained optimization problems. The proposed method satisfies the sufficient decent property irrespective of the line search and the global convergence was established under some suitable. Further, the new method was used to train different sets of data via a feed forward neural network. Results obtained show that the proposed algorithm significantly reduces the computational time by speeding up the directional minimization with a faster convergence rate.","PeriodicalId":37156,"journal":{"name":"Mathematical Modeling and Computing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Performance evaluation of a novel Conjugate Gradient Method for training feed forward neural network\",\"authors\":\"K. Kamilu, M. I. Sulaiman, A. Muhammad, A. W. Mohamad, M. Mamat\",\"doi\":\"10.23939/mmc2023.02.326\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we construct a new conjugate gradient method for solving unconstrained optimization problems. The proposed method satisfies the sufficient decent property irrespective of the line search and the global convergence was established under some suitable. Further, the new method was used to train different sets of data via a feed forward neural network. Results obtained show that the proposed algorithm significantly reduces the computational time by speeding up the directional minimization with a faster convergence rate.\",\"PeriodicalId\":37156,\"journal\":{\"name\":\"Mathematical Modeling and Computing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Mathematical Modeling and Computing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.23939/mmc2023.02.326\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"Mathematics\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Mathematical Modeling and Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.23939/mmc2023.02.326","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Mathematics","Score":null,"Total":0}

引用次数: 1

摘要

本文构造了求解无约束优化问题的一种新的共轭梯度法。该方法与线搜索无关，满足足够的体面性，并在一定条件下证明了算法的全局收敛性。此外，该方法还通过前馈神经网络对不同的数据集进行训练。结果表明，该算法通过加快方向最小化速度和更快的收敛速度显著减少了计算时间。

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

Performance evaluation of a novel Conjugate Gradient Method for training feed forward neural network

In this paper, we construct a new conjugate gradient method for solving unconstrained optimization problems. The proposed method satisfies the sufficient decent property irrespective of the line search and the global convergence was established under some suitable. Further, the new method was used to train different sets of data via a feed forward neural network. Results obtained show that the proposed algorithm significantly reduces the computational time by speeding up the directional minimization with a faster convergence rate.

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

Mathematical Modeling and Computing Computer Science-Computational Theory and Mathematics

CiteScore

1.60

自引率

0.00%

发文量