Affiliated with RCfalse
Towards implementation of residual-feedback GMDH neural network on parallel GPU memory guided by a regression curve
Ricardo Brito1; Simon Fong1; Kyungeun Cho2; Wei Song3; Raymond Wong4; Sabah Mohammed5; Jinan Fiaidhi5
Source PublicationJournal of Supercomputing

GMDH, which stands for Group Method Data Handling, is an evolutionary type of neural network. It has received much attention in the supercomputing research community because of its ability to optimize its internal structure for maximum prediction accuracy. GMDH works by evolving itself from a basic network, expanding its number of neurons and hidden layer until no further performance gain can be obtained. Earlier on, the authors proposed a novel strategy that extends existing GMDH neural network techniques. The new strategy, called residual-feedback, retains and reuses past prediction errors as part of the multivariate sample data that provides relevant multivariate inputs to the GMDH neural networks. This is important because the strength of GMDH, like any neural network, is in predicting outcomes from multivariate data, and it is very noise-tolerant. GMDH is a well-known ensemble type of prediction method that is capable of modeling highly non-linear relations. Maximum accuracy is often achieved by using only the minimum amount of network neurons and simplest layered structure. This paper contributes to the technical design of implementing GMDH on GPU memory where all the weight computations run on parallel GPU memory blocks. It is a first step towards developing complex neural network architecture on GPU with the capability of evolving and expanding its structure to minimally sufficient for obtaining the maximum prediction accuracy based on the given input data.

KeywordArtificial Neural Networks Gmdh Parallel Execution Nvidia Cuda Gpu
URLView the original
Indexed BySCIE
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:000385417400016
Scopus ID2-s2.0-84969835796
Fulltext Access
Citation statistics
Cited Times [WOS]:2   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
Corresponding AuthorSimon Fong
Affiliation1.Department of Computer and Information Science,University of Macau,Taipa, Macau SAR,Macao
2.Department of Computer and Multimedia Engineering,Dongguk University,Seoul,South Korea
3.College of Information Engineering,North China University of Technology,Beijing,China
4.School of Computer Science and Engineering,University of New South Wales,Sydney,Australia
5.Department of Computer Science,Lakehead University,Thunder Bay,Canada
First Author AffilicationUniversity of Macau
Corresponding Author AffilicationUniversity of Macau
Recommended Citation
GB/T 7714
Ricardo Brito,Simon Fong,Kyungeun Cho,et al. Towards implementation of residual-feedback GMDH neural network on parallel GPU memory guided by a regression curve[J]. Journal of Supercomputing,2016,72(10):3993-4020.
APA Ricardo Brito,Simon Fong,Kyungeun Cho,Wei Song,Raymond Wong,Sabah Mohammed,&Jinan Fiaidhi.(2016).Towards implementation of residual-feedback GMDH neural network on parallel GPU memory guided by a regression curve.Journal of Supercomputing,72(10),3993-4020.
MLA Ricardo Brito,et al."Towards implementation of residual-feedback GMDH neural network on parallel GPU memory guided by a regression curve".Journal of Supercomputing 72.10(2016):3993-4020.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Ricardo Brito]'s Articles
[Simon Fong]'s Articles
[Kyungeun Cho]'s Articles
Baidu academic
Similar articles in Baidu academic
[Ricardo Brito]'s Articles
[Simon Fong]'s Articles
[Kyungeun Cho]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Ricardo Brito]'s Articles
[Simon Fong]'s Articles
[Kyungeun Cho]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

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