CAJ | 학술논문

假设检验中Neyman-Pearson准则是一种基于似然比的信号检测、识别、分类方法.神经网络是实现这种判定准则的优选方案，但是传统的最小平方学习算法，如BP算法等,往往不能取得全局最优解. 针对一种非最小平方学习算法，提出了一种概率分配原则，并给出了一种Neyman-Pearson准则的神经网络实现新算法. 对新算法在假设检验中的应用进行了仿真验证. 结果表明新算法具有更小的误差，更加适用于Neyman-Pearson准则.
가설검험중Neyman-Pearson준칙시일충기우사연비적신호검측、식별、분류방법.신경망락시실현저충판정준칙적우선방안，단시전통적최소평방학습산법，여BP산법등,왕왕불능취득전국최우해. 침대일충비최소평방학습산법，제출료일충개솔분배원칙，병급출료일충Neyman-Pearson준칙적신경망락실현신산법. 대신산법재가설검험중적응용진행료방진험증. 결과표명신산법구유경소적오차，경가괄용우Neyman-Pearson준칙.
Presents the Neyman-Pearson criterion in hypothesis testing based on the probability rate for problems such as classification, detection, and pattern recognition as an improved kind of nonleast-square learning algorithm to decide the criterion of the probability distribution and gives a better algorithm based on the absolute error and concludes from simulation results that the new algorithm has less error and is more suitable for Neyman-Pearson criterion.