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 證明了pnn的決策函數(shù)依概率收斂于貝葉斯決策函數(shù);給出了pnn的推廣能力表達式;證明了一個分類網絡的測試集正確率是該網絡推廣能力的極大似然估計;給出了分類網絡中需要的測試集數(shù)目表達式;證明了pnn推廣能力不大于由貝葉斯決策所帶來的正確識別率