C-pruner: an improved instance pruning algorithm
Keping Zhao, Shuigeng Zhou, Jihong Guan, Aoying Zhou · 2004
Instance-based learning faces the problem of deciding which instances could be discarded in order to save computation and storage costs. For large instance bases classifier suffers from large memory requirements and slow response. And present noisy instances may deteriorate the classification accuracy. This paper analyzes the strength and weakness of some of the existing algorithms for instance pruning, and propose an improved method C-Pruner. Experiments over real-world datasets verify C-pruner's superior to the existing methods in classification accuracy.