RBF神经网络隐层冗余容错方法  

Hidden-layer Redundancy Method of RBF Neural Networks

作　　者：许荔秦[1] 胡东成[1] 

机构地区：[1]清华大学自动化系,北京100084

出　　处：《控制与决策》2001年第5期591-594,598,共5页Control and Decision

摘　　要：首先提出 RBF隐层节点冗余结构 ,然后分别分析在单故障和普遍故障下的网络特性 ,并证明了这种结构可以有效容错 ,最后提出了实用的隐层冗余方法 ,并经仿真实验证明是可行的。A hidden-layer neuron redundancy architecture of RBF network is presented. Performance of the network are analyzed under both single-fault and universal faults. The performance of the network under faults can be improved significantly with this redundancy architecture. Finally, a practical method of redundancy of hidden-layer neurons to gain fault tolerance is presented. Simulation results show the validity of the method.

关 键 词：容错 冗余 多层感知器 径向基神经网络 学习算法 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]