Dynamic Structural Neural Network

De Montfort University Open Research Archive

Show simple item record

dc.contributor.author Chiclana, Francisco en
dc.contributor.author Cu Nguyen, Giap en
dc.contributor.author Le Hoang, Son en
dc.date.accessioned 2017-12-19T09:31:53Z
dc.date.available 2017-12-19T09:31:53Z
dc.date.issued 2017-12
dc.identifier.citation Cu Nguyen, G., Le Hoang, S., Chiclana, F. (2017) Dynamic Structural Neural Network. Journal of Intelligent and Fuzzy Systems . Accepted on 12th December 2017 en
dc.identifier.issn 1064-1246
dc.identifier.issn 1875-8967
dc.identifier.uri http://hdl.handle.net/2086/15018
dc.description The file attached to this record is the author's final peer reviewed version. en
dc.description.abstract Artificial 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.language.iso en_US en
dc.publisher IOS Press en
dc.subject Artificial neural network en
dc.subject Binary multi-input multi-output problems en
dc.subject Dynamic structure en
dc.subject Genetic algorithm en
dc.subject Greedy algorithm en
dc.subject Medical diagnosis en
dc.title Dynamic Structural Neural Network en
dc.type Article en
dc.researchgroup Centre for Computational Intelligence en
dc.peerreviewed Yes en
dc.explorer.multimedia No en
dc.funder This 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.projectid This 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.cclicence CC-BY-NC en
dc.date.acceptance 2017-12-12 en


Files in this item

This item appears in the following Collection(s)

Show simple item record