提出了一种根据粗糙集理论进行ＢＰ网络设计的方法，它结合了粗糙集理论的强大的定性分析能力和ＢＰ网络的准确的逼近能力，得到一种可理解性好、计算简单、收敛速度快的神经网络模型．这种神经网络的学习算法的要点是：应用粗糙集的理论和方法，从给定学习样本数据中发现一组规则，并根据这些规则去建立网络模型中相应的隐层节点；然后用ＢＰ算法迭代求出网络的参数，从而完成网络的设计 A method of BP network design based on rough set theory is proposed. Combining the strong qualitative analysis ability of rough set theory and the accurate approximation ability of BP network, a method with good comprehensibility, simple calculation and fast convergence speed Neural network model. The main points of this neural network learning algorithm are: to apply rough set theory and method to find a set of rules from a given learning sample data and to establish corresponding hidden nodes in the network model according to these rules; and then use BP algorithm Iterative parameters of the network to complete the network design