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.

• 基于此种考虑,本文提出了样本受零均值噪声影响下的学习理论的关键定理,并讨论了零均值噪声样本下的学习过程一致收敛速度的界。