the rule extraction of neural networks is discussed, which is an effective method to avoid shortcoming of being “ black boxes ” . techniques based on decompositional and input-output mapping approaches are studied, their fundamental concepts and pedagogical rule extraction are compared in detail 神经网络中的规则提取方法是解决“黑箱问题”的有效手段,论文分析了基于结构分解和基于输入输出映射的神经网络规则提取的基本思想和对应的各种算法,并对它们的性能进行比较。