CASIA OpenIR  > 复杂系统管理与控制国家重点实验室  > 先进机器人
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
Source PublicationNEUROCOMPUTING
2015-02-03
Volume149Issue:APages:29-38
SubtypeArticle
AbstractThe 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.
KeywordNeural Network Ensemble Particle Swarm Optimization Differential Evolution Artificial Bee Colony Chaotic Search
WOS HeadingsScience & Technology ; Technology
DOI10.1016/j.neucom.2013.12.062
WOS KeywordCOLONY ABC ALGORITHM ; DIFFERENTIAL EVOLUTION ; OPTIMIZATION
Indexed BySCI
Language英语
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000360028800005
Citation statistics
Cited Times:7[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/8957
Collection复杂系统管理与控制国家重点实验室_先进机器人
Affiliation1.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
Recommended Citation
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.
Files in This Item: Download All
File Name/Size DocType Version Access License
86-Evolved neural ne(1108KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhao, Zeng-Shun]'s Articles
[Feng, Xiang]'s Articles
[Lin, Yan-yan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhao, Zeng-Shun]'s Articles
[Feng, Xiang]'s Articles
[Lin, Yan-yan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhao, Zeng-Shun]'s Articles
[Feng, Xiang]'s Articles
[Lin, Yan-yan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 86-Evolved neural network ensemble by multiple heterogeneous swarm intelligence.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.