Gabrys, B., 2004. Learning hybrid neuro-fuzzy classifier models from data: to combine or not to combine? Fuzzy Sets and Systems, 147 (1), pp. 39-56.
Full text not available from this repository.
Official URL: http://www.sciencedirect.com/science?_ob=ArticleUR...
To combine or not to combine? This very important question is examined in this paper in the context of a hybrid neuro-fuzzy pattern classifier design process. A general fuzzy min–max neural network with its basic learning procedure is used within five different algorithm-independent learning schemes. Various versions of cross-validation and resampling techniques, leading to generation of a single classifier or a multiple classifier system, are scrutinised and compared. The classification performance on unseen data, commonly used as a criterion for comparing different competing designs, is augmented by further four criteria attempting to capture various additional characteristics of classifier generation schemes. These include: the ability to estimate the true classification error rate, the classifier transparency, the computational complexity of the learning scheme and the potential for adaptation to changing environments and new classes of data. One of the main questions examined is whether and when to use a single classifier or a combination of a number of component classifiers within a multiple classifier system.
|Additional Information:||This is an invited, extended version of the paper from the EUNITE'2001 conference published in this established, highly regarded, high impact journal. In this paper a number of different distinctive algorithms for building GFMM classifiers and GFMM ensembles are discussed and compared with regard to an extended criteria which not only include the classification performance but power and ability of various algorithm independent learning schemes to provide accurate estimation of the error, the scheme readiness for true on-line adaptation to changing environments, computational complexity of the learning and final classifier system decision making transparency. Our various previously proposed approaches are scrutinised with regard to all of those criteria and in the context of the requirements for future general framework for self-adpating and monitoring classification and prediction systems pursued in a number of current projects.|
|Subjects:||Generalities > Computer Science and Informatics > Artificial Intelligence|
Generalities > Computer Science and Informatics
|Group:||School of Design, Engineering & Computing > Smart Technology Research Centre|
|Deposited By:||INVALID USER|
|Deposited On:||17 Dec 2007|
|Last Modified:||07 Mar 2013 14:35|
|Repository Staff Only -|
|BU Staff Only -|
|Help Guide -||Editing Your Items in BURO|