Improvement flower pollination extreme learning machine based on meta-learning

Sarunyoo Boriratrit, S. Chiewchanwattana, K. Sunat, Pakarat Musikawan, Punyaphol Horata
{"title":"Improvement flower pollination extreme learning machine based on meta-learning","authors":"Sarunyoo Boriratrit, S. Chiewchanwattana, K. Sunat, Pakarat Musikawan, Punyaphol Horata","doi":"10.1109/JCSSE.2016.7748871","DOIUrl":null,"url":null,"abstract":"Extreme Learning Machine (ELM) model which learn very faster than other neural networks model but the solution was not suitable as expected since the randomness of the input weights and biases may cause to the nonfulfillment of solution. Flower Pollination Extreme Learning Machine (FP-ELM) model that it was merged by ELM and Flower Pollination Algorithm (FPA) to adjust the input weight and biases for improve performance of output weight when the input weight and biases were calculated. Nonetheless, FP-ELM may cause overfitting and more number of hidden nodes were used. In this paper, Meta Learning of Flower Pollination Extreme Learning Machine (Meta-FPELM) was proposed that compart the input weight, calculate to hidden nodes as FP-ELM and combine to the last output weight. In addition, the result of real word regression problems experiment of Meta-FPELM compared with state-of-the-art show that Meta-FPELM can overcome five-eighth in testing phase for all datasets.","PeriodicalId":321571,"journal":{"name":"2016 13th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"191 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 13th International Joint Conference on Computer Science and Software Engineering (JCSSE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/JCSSE.2016.7748871","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

Abstract

Extreme Learning Machine (ELM) model which learn very faster than other neural networks model but the solution was not suitable as expected since the randomness of the input weights and biases may cause to the nonfulfillment of solution. Flower Pollination Extreme Learning Machine (FP-ELM) model that it was merged by ELM and Flower Pollination Algorithm (FPA) to adjust the input weight and biases for improve performance of output weight when the input weight and biases were calculated. Nonetheless, FP-ELM may cause overfitting and more number of hidden nodes were used. In this paper, Meta Learning of Flower Pollination Extreme Learning Machine (Meta-FPELM) was proposed that compart the input weight, calculate to hidden nodes as FP-ELM and combine to the last output weight. In addition, the result of real word regression problems experiment of Meta-FPELM compared with state-of-the-art show that Meta-FPELM can overcome five-eighth in testing phase for all datasets.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于元学习的花授粉极限学习机改进
极限学习机(Extreme Learning Machine, ELM)模型的学习速度比其他神经网络模型快,但由于输入权值的随机性和偏置可能导致解的不满足,其解不符合预期。花授粉极限学习机(FP-ELM)模型,在计算输入权值和偏值时,将ELM与花授粉算法(FPA)合并,调整输入权值和偏值,以提高输出权值的性能。然而,FP-ELM可能会导致过拟合,并且使用了更多的隐藏节点。本文提出了花授粉极限学习机的元学习(Meta- fpelm),将输入权值进行比较,计算到隐藏节点作为FP-ELM,并结合到最后的输出权值。此外,Meta-FPELM的真实单词回归问题实验结果与目前的研究结果进行了比较,结果表明,Meta-FPELM在所有数据集的测试阶段都能克服5 / 8的问题。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Extended hierarchical extreme learning machine with multilayer perceptron Pill image binarization for detecting text imprints An approach for density monitoring of brown planthopper population in simulated paddy fields Impact of wireless communications technologies on elder people healthcare: Smart home in Australia Energy-aware scheduling of multiple workflows application on distributed systems
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1