Evolved neural network ensemble by multiple heterogeneous swarm intelligence
Zhao, Zeng-Shun1,3; Feng, Xiang1; Lin, Yan-yan1; Wei, Fang1; Wang, Shi-Ku1; Xiao, Tong-Lu1; Cao, Mao-Yong1; Hou, Zeng-Guang2
2015-02-03
发表期刊NEUROCOMPUTING
卷号149期号:A页码:29-38
文章类型Article
摘要The neural network ensemble (NINE) is a very effective way to obtain a good prediction performance by combining the outputs of several independently trained neural networks. Swarm intelligence is applied here to model the population of interacting agents or swarms that are able to self-organize. In this paper, we combine NNE and multi-population swarm intelligence to construct our improved neural network ensemble (INNE). First, each component forward neural network (FNN) is optimized by chaotic particle swarm optimization (CPSO) and gradient gescending (GD) algorithm. Second, in contrast to most existing NNE training algorithm, we adopt multiple obviously different populations to construct swarm intelligence. As an example, one population is trained by particle swarm optimization (PSO) and the others are trained by differential evolution (DE) or artificial bee colony algorithm (ABC). The ensemble weights are trained by multi-population co-evolution PSO-ABC-DE chaotic searching algorithm (M-PSO-ABC-DE-CS). Our experiments demonstrate that the proposed novel INNE algorithm is superior to existing popular NNE in function prediction. (C) 2014 Elsevier B.V. All rights reserved.
关键词Neural Network Ensemble Particle Swarm Optimization Differential Evolution Artificial Bee Colony Chaotic Search
WOS标题词Science & Technology ; Technology
DOI10.1016/j.neucom.2013.12.062
关键词[WOS]COLONY ABC ALGORITHM ; DIFFERENTIAL EVOLUTION ; OPTIMIZATION
收录类别SCI
语种英语
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence
WOS记录号WOS:000360028800005
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/8957
专题复杂系统管理与控制国家重点实验室_先进机器人
作者单位1.Shandong Univ Sci & Technol, Coll Elect Commun & Phys, Qingdao 266590, Peoples R China
2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
3.Shandong Univ, Sch Control Sci & Engn, Jinan 250061, Peoples R China
推荐引用方式
GB/T 7714
Zhao, Zeng-Shun,Feng, Xiang,Lin, Yan-yan,et al. Evolved neural network ensemble by multiple heterogeneous swarm intelligence[J]. NEUROCOMPUTING,2015,149(A):29-38.
APA Zhao, Zeng-Shun.,Feng, Xiang.,Lin, Yan-yan.,Wei, Fang.,Wang, Shi-Ku.,...&Hou, Zeng-Guang.(2015).Evolved neural network ensemble by multiple heterogeneous swarm intelligence.NEUROCOMPUTING,149(A),29-38.
MLA Zhao, Zeng-Shun,et al."Evolved neural network ensemble by multiple heterogeneous swarm intelligence".NEUROCOMPUTING 149.A(2015):29-38.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
86-Evolved neural ne(1108KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhao, Zeng-Shun]的文章
[Feng, Xiang]的文章
[Lin, Yan-yan]的文章
百度学术
百度学术中相似的文章
[Zhao, Zeng-Shun]的文章
[Feng, Xiang]的文章
[Lin, Yan-yan]的文章
必应学术
必应学术中相似的文章
[Zhao, Zeng-Shun]的文章
[Feng, Xiang]的文章
[Lin, Yan-yan]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 86-Evolved neural network ensemble by multiple heterogeneous swarm intelligence.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。