介绍一种用循环多层感知器神经网络实现符号逻辑推理系统的方法。
A method of implementing symbol logic inference system using recurrent multilayer perceptron neural networks is presented in this paper.
对不能识别的样本,采用模糊推理技术,把传统的直观特征识别结果和多层BP网络结果在特征级上融合,提高系统的性能。
As to the samples that have not been able to be recognized we adopt fuzzy logic to fusion obvious feature and MBPNN's feature, and increase the performance of the system.
本文还详细介绍了一种用多层前向神经网络实现模糊逻辑的自适应神经网络模糊推理系统——ANFIS,并用它来分析、验证神经模糊控制的控制效果。
This paper also stated the method of Adaptive Neural-Fuzzy Inference System (ANFIS) in details, which was used to analysis and testify effect of the NN-FC.
应用推荐