摘要
从大量应用实例中总结归纳出了一个初定有教师的线性基本函数前向三层神经网络隐节点数的经验公式，提出了一种判断所选隐节点数是否多余的新方法。最后用两个实例予以验证。
:An empirical formula for initially selecting the number of hidden nodes of supervised linear basis function (LBF)feedforward three-layered neural networks is summarized and induced according to many application examples and a new method for judging whether there exist redundant hidden nodes in the hidden layer of such a neural network is proposed.At the end,two examples are given to verify the above formula and method.
出处
《电路与系统学报》
CSCD
1997年第3期31-37,共7页
Journal of Circuits and Systems
关键词
线性基本函数
神经网络
拓扑结构
经验公式
误差
:Linear basis fuction,Neural Networks,Topological structures,Empirical formula,Error.
