Bounds on the rate of uniform convergence of learning processes with equality-expect noise samples on quasi-probability space
Er-ling Du, Yingxin Wang, Ming-Hu Ha · 2009
The bounds on the rate of uniform convergence of learning processes play an important role in the Statistical Learning Theory. They provide theoretical bases for the application of support vector machine and reflect the generalization ability of the learning machines. This paper mainly deals with the bounds on the rate of uniform convergence of learning processes when samples are corrupted by equality-expect noise on quasi-probability space.