【摘要】 针对一类以往的聚类算法不能很好的优化输入空间的问题,从模型简化的思想出发,充分考虑了样本输出对系统的作用,将无导师的学习算法与基于梯度的信息寻优算法相结合,并根据数据分布的密度自适应的调整聚类点的分布情况.给出了基于该算法的T-S模糊神经网络实现,并以函数逼近为例说明新算法在自适应能力,建模精度及计算量等方面均优于原算法.从而达到优化系统结构的目的.更多还原

【Abstract】 In accordance with the problem that the past clustering method can not optimize the input space of fuzzy model, firstly this paper considers the influence of sample’s outputs upon the model. Secondly the paper combines the nonsupervised algorithm and the gradient based algorithm. Thirdly we adjust the distributing condition of the clustering point according to the density of data’ s distribution in order to optimize the model’s structure. Finally we construct a model based on T-S Fuzzy and Neural networks and focus on function approximation problems to evalute its performed. In the process we can draw the conclusion that the new algorithm is better than the old one in adaptation, computational complexity and the modeling accuracy.更多还原