Dynamic Structural Neural Network

dc.cclicenceCC-BY-NCen
dc.contributor.authorChiclana, Franciscoen
dc.contributor.authorCu Nguyen, Giapen
dc.contributor.authorLe Hoang, Sonen
dc.date.acceptance2017-12-12en
dc.date.accessioned2017-12-19T09:31:53Z
dc.date.available2017-12-19T09:31:53Z
dc.date.issued2017-12
dc.descriptionThe file attached to this record is the author's final peer reviewed version.en
dc.description.abstractArtificial neural network (ANN) has been well applied in pattern recognition, classification and machine learning thanks to its high performance. Most ANNs are designed by a static structure whose weights are trained during a learning process by supervised or unsupervised methods. These training methods require a set of initial weights values, which are normally randomly generated, with different initial sets of weight values leading to different convergent ANNs for the same training set. Dealing with these drawbacks, a trend of dynamic ANN was invoked in the past year. However, they are either too complex or far from practical applications such as in the pathology predictor in binary multi-input multi-output (MIMO) problems, when the role of a symptom is considered as an agent, a pathology predictor’s outcome is formed by action of active agents while other agents’ activities seem to be ignored or have mirror effects. In this paper, we propose a new dynamic structural ANN for MIMO problems based on the dependency graph, which gives clear cause and result relationships between inputs and outputs. The new ANN has the dynamic structure of hidden layer as a directed graph showing the relation between input, hidden and output nodes. The properties of the new dynamic structural ANN are experienced with a pathology problem and its learning methods’ performances are compared on a real well known dataset. The result shows that both approaches for structural learning process improve the quality of ANNs during learning iteration.en
dc.explorer.multimediaNoen
dc.funderThis research is funded by Graduate University of Science and Technology under grant number GUST.STS.ÐT2017- TT02. The authors are grateful for the support from the Institute of Information Technology, Vietnam Academy of Science and Technology. We received the necessary devices as experiment tools to implement proposed method.en
dc.identifier.citationCu Nguyen, G., Le Hoang, S., Chiclana, F. (2017) Dynamic structural neural network. Journal of Intelligent & Fuzzy Systems, 34(4), pp.2479–2490.en
dc.identifier.doihttps://doi.org/10.3233/jifs-171947
dc.identifier.issn1064-1246
dc.identifier.issn1875-8967
dc.identifier.urihttp://hdl.handle.net/2086/15018
dc.language.isoen_USen
dc.peerreviewedYesen
dc.projectidThis research is funded by Graduate University of Science and Technology under grant number GUST.STS.ÐT2017- TT02. The authors are grateful for the support from the Institute of Information Technology, Vietnam Academy of Science and Technology. We received the necessary devices as experiment tools to implement proposed method.en
dc.publisherIOS Pressen
dc.researchgroupCentre for Computational Intelligenceen
dc.researchinstituteInstitute of Artificial Intelligence (IAI)en
dc.subjectArtificial neural networken
dc.subjectBinary multi-input multi-output problemsen
dc.subjectDynamic structureen
dc.subjectGenetic algorithmen
dc.subjectGreedy algorithmen
dc.subjectMedical diagnosisen
dc.titleDynamic Structural Neural Networken
dc.typeArticleen

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
jifs17-1947.pdf
Size:
546.83 KB
Format:
Adobe Portable Document Format
Description:
Author's copy of accepted paper.
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
4.2 KB
Format:
Item-specific license agreed upon to submission
Description: