模糊优选神经网络及其在综合后评价中的应用

将模糊优选理论与神经网络理论相结合，确定网络拓扑结构：隐含层数、隐含层节点数与节点激励函数的合理模式。将模糊优选的相对优属度模型作为人工神经网络的激励函数，建立模糊优选神经网络权重调整BP模型，实证研究表明，模糊优选BP神经网络模型，可以较好地应用于综合后评价。

Fuzzy optimum selection-based BP neural network and its application to comprehensive post-evaluation

The theory of fuzzy optimum selection is combined with the neural network theory, and the topologic structure of the network is determined, including the number of implicit layers, node number of implicit layers, and the reasonable mode of the node stimulation function. The comparative membership grade model for fuzzy optimum selection is taken as the stimulation function of the artificial neural network, and a weight adjustable BP model based on the neural network for fuzzy optimum selection is developed. Case study shows that the present model can be successfully applied to comprehensive post-evaluation.