有教师的线性基本函数前向三层神经网络结构研究  

On Structures of Supervised Linear Basis FunctionFeedforward Three-Layered Neural Networks

作　　者：高大启[1] 

机构地区：[1]江苏理工大学信息科学研究所

出　　处：《电路与系统学报》1997年第3期31-37,共7页Journal of Circuits and Systems

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.

关 键 词：线性基本函数 神经网络 拓扑结构 经验公式 误差 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]