Gradient learning dynamics of radial basis function networks
梯度算法下RBF网的参数变化动态

To understand the dynamic behavior and improve the structure and performance of neural networks,it is very important to investigate their parameter changing dynamics during the learning.For radial basis function(RBF)networks using gradient descent method to minimize the least squares error cost function,this paper discusses the learning dynamics of the hidden unit parameters,i.e.,their possible values after learning.It is proved that if the cost function is not zero after the algorithm converges,then all hidden units will move to the weighted cluster centers of sample inputs.If cost function is zero,then hidden units will have shrinking,eliminating,out-moving and overlapping happened to those redundant units. Further simulation shows that such phenomena occur frequently in oversized RBF networks.