一种基于Walsh变换的反馈过程神经网络模型及学习算法  

A Feedback Procedure Neural Network Model Based on Walsh Conversion and Its Learning Algorithm

作　　者：许增福 梁静国[1] 李盼池[2] 许少华[2] 

机构地区：[1]哈尔滨工程大学经济管理学院,黑龙江哈尔滨150001 [2]大庆石油学院计算机学院,黑龙江大庆163318

出　　处：《信息与控制》2004年第4期404-407,412,共5页Information and Control

基　　金：国家自然科学基金资助项目 ( 60 3 73 10 2 )

摘　　要：提出了一种带有反馈输入的过程式神经元网络模型 ,模型为三层结构 ,其隐层和输出层均为过程神经元 .输入层完成连续信号的输入 ,隐层完成输入信号的空间聚合和向输出层逐点映射 ,并将输出信号逐点反馈到输入层 ;输出层完成隐层输出信号的时、空聚合运算和系统输出 .在对权函数实施Walsh变换的基础上给出了该模型的学习算法 .仿真实验证明了模型和算法的有效性 .A feedback procedure neural network model (FPNN) is proposed. The FPNN has three layers, and its hidden layer and output layer are composed of procedure neurons. The input layer accomplishes continuous signal input, while the hidden layer accomplishes input signal aggregation in space and transfers the input signals to the output layer. Then the hidden layer transfers its own output to the input layer, both point by point. The output layer accomplishes output signal aggregation in both space and time, and fulfills system output. A learning algorithm is pre sented based on Walsh conversion of weight function. Simulation experiment proves the availability and effectiveness of the model and algorithm.

关 键 词：过程神经元 反馈网络 WALSH变换 学习算法 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]