Some Theoretical Studies On Learning Theory With Samples Corrupted By Zero-expect Noise

The key theorem and the bounds on the rate of convergence of learning processes provide theoretical bases for the applied research of support vector machine etc., so they play important roles in statistical learning theory. In the study of these two aspects, samples which we deal with are supposed to be noise-free. But it is not always the case because of the influence of human or environmental factors. With a view of this, we propose the key theorem and discuss the bounds on the rate of uniform convergence of learning processes based on ERM principle when samples are corrupted by zero-expect noise.