2002 · 201 citations · 4 references
ComputingComputer ScienceData MiningMachine LearningStatistical LearningClassificationDimensionality ReductionOptimization For Machine LearningPattern RecognitionSupervised LearningSupport Vector MachinesSimplificationSupport Vector Machine ClassificationSupport Vector Regression
This paper demonstrates that standard algorithms for training support vector machines generally produce solutions with a greater number of support vectors than are strictly necessary. An algorithm is presented that allows unnecessary support vectors to be recognized and eliminated while leaving the solution otherwise unchanged. The algorithm is applied to a variety of benchmark data sets (for both classification and regression) and in most cases the procedure leads to a reduction in the number of support vectors. In some cases the reduction is substantial.
4
Yuhai Wu, Vladimir Vapnik · Technometrics · 1999 · 27K citations
Incremental learning with support vector machines
Stefan Rüping · 2002 · 532 citations