• Login
    View Item 
    •   DORA Home
    • Faculty of Computing, Engineering and Media
    • School of Computer Science and Informatics
    • View Item
    •   DORA Home
    • Faculty of Computing, Engineering and Media
    • School of Computer Science and Informatics
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Dynamic Structural Neural Network

    Thumbnail
    View/Open
    Author's copy of accepted paper. (546.8Kb)
    Date
    2017-12
    Author
    Chiclana, Francisco;
    Cu Nguyen, Giap;
    Le Hoang, Son
    Metadata
    Show attachments and full item record
    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.
    Description
    The file attached to this record is the author's final peer reviewed version.
    Citation : Cu Nguyen, G., Le Hoang, S., Chiclana, F. (2017) Dynamic structural neural network. Journal of Intelligent & Fuzzy Systems, 34(4), pp.2479–2490.
    URI
    http://hdl.handle.net/2086/15018
    DOI
    https://doi.org/10.3233/jifs-171947
    ISSN : 1064-1246
    1875-8967
    Research Group : Centre for Computational Intelligence
    Research Institute : Institute of Artificial Intelligence (IAI)
    Peer Reviewed : Yes
    Collections
    • School of Computer Science and Informatics [2679]

    Submission Guide | Reporting Guide | Reporting Tool | DMU Open Access Libguide | Take Down Policy | Connect with DORA
    DMU LIbrary
     

     

    Browse

    All of DORACommunities & CollectionsAuthorsTitlesSubjects/KeywordsResearch InstituteBy Publication DateBy Submission DateThis CollectionAuthorsTitlesSubjects/KeywordsResearch InstituteBy Publication DateBy Submission Date

    My Account

    Login

    Submission Guide | Reporting Guide | Reporting Tool | DMU Open Access Libguide | Take Down Policy | Connect with DORA
    DMU LIbrary