UM
Towards implementation of residual-feedback GMDH neural network on parallel GPU memory guided by a regression curve
Brito R.1; Fong S.1; Cho K.5; Song W.2; Wong R.3; Mohammed S.4; Fiaidhi J.4
2016-10-01
Source PublicationJournal of Supercomputing
ISSN15730484 09208542
Volume72Issue:10Pages:3993-4020
AbstractGMDH, 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 CUDA GMDH GPU NVIDIA Parallel execution
DOI10.1007/s11227-016-1740-9
URLView the original
Language英語
Fulltext Access
Citation statistics
Cited Times [WOS]:2   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionUniversity of Macau
Affiliation1.Universidade de Macau
2.North China University of Technology
3.University of New South Wales (UNSW) Australia
4.Lakehead University
5.Dongguk University, Seoul
Recommended Citation
GB/T 7714
Brito R.,Fong S.,Cho K.,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 Brito R..,Fong S..,Cho K..,Song W..,Wong R..,...&Fiaidhi J..(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 Brito R.,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.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Brito R.]'s Articles
[Fong S.]'s Articles
[Cho K.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Brito R.]'s Articles
[Fong S.]'s Articles
[Cho K.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Brito R.]'s Articles
[Fong S.]'s Articles
[Cho K.]'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.