The convergence of the pnn decision rule for the bayesian decision rule is proved with probability . an explicit formulation of pnn generalization ability is proposed . and the accuracy rate of a classification network is explained as the maximum likelihood estimation of the generalization ability 证明了pnn的决策函数依概率收敛于贝叶斯决策函数;给出了pnn的推广能力表达式;证明了一个分类网络的测试集正确率是该网络推广能力的极大似然估计;给出了分类网络中需要的测试集数目表达式;证明了pnn推广能力不大于由贝叶斯决策所带来的正确识别率
