Accession Number : ADA259921


Title :   A Novel Recursive Partitioning Criterion


Descriptive Note : Technical rept.,


Corporate Author : BROWN UNIV PROVIDENCE RI DEPT OF PHYSICS


Personal Author(s) : Perrone, Michael P


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a259921.pdf


Report Date : 23 Dec 1992


Pagination or Media Count : 7


Abstract : A data-driven algorithm for partitioning many-class classification problems is presented. The algorithm generates tree-structured hybrid networks with controller nets at tree branches and local expert nets at the leaves. The controller nets recursively partition the feature space according to a novel misclassification minimization rule designed to create groupings of the classes which simplify the classification task. Each local expert is trained only on a subset of the training data corresponding to one of the partitions. The advantage to this approach is that the classification task that each local expert performs is greatly simplified. This simplification helps to avoid the curse of dimensionality and scaling problems by allowing the local expert nets to focus their search for structure in a small portion of the input space.... Cart, Recursive partitioning, Hybrid networks, Misclassification matrix.


Descriptors :   *ALGORITHMS , *NEURAL NETS , *CLASSIFICATION , *HYBRID SYSTEMS , *SEPARATION , INPUT , SIMPLIFICATION , APPROACH , TREES


Subject Categories : Operations Research


Distribution Statement : APPROVED FOR PUBLIC RELEASE