O.L. Chacon, N.R. Padilla, and E. Vazquez (Mexico)
Classification, vector support, fuzzy clustering.
The support vector machine SVM ¯ has exhibited excellent generalization as classifier for linearly and non-linearly separable data sets. One drawback in using nonlinear SVM is the steep growth of the number of support vectors with increasing size of the training sets requiring long compu tational time and large amount of memory. In this work an initial data set reduction through a clustering process is proposed to overcome this problem.
Important Links:
Go Back
