复指数Fourier神经元网络隐神经元衍生算法  

Complex-exponential Fourier neuronal network and its hidden-neuron growing algorithm

作　　者：张雨浓[1] 曾庆淡[1] 肖秀春[1] 姜孝华[1] 邹阿金[1] 

机构地区：[1]中山大学信息科学与技术学院,广州510275

出　　处：《计算机应用》2008年第10期2503-2506,共4页journal of Computer Applications

基　　金：国家自然科学基金资助项目(60643004;60775050);中山大学科研启动费资助项目;中山大学后备重点课题资助项目

摘　　要：以平方可积空间上的复指数Fourier级数作为激励函数构造了新型Fourier神经元网络,并推导出采用加号逆表示的网络权值直接确定公式,克服了传统BP神经网络收敛速度慢、易陷于局部极小点、迭代学习易发生振荡等缺陷。并在此基础上构造了隐神经元衍生算法,克服了传统BP神经网络难以确定最优网络拓扑结构的缺点。理论分析及仿真实验表明,该复指数Fourier神经元网络能够一步计算网络最优权值且能自适应调整网络结构,对随机加性噪声具有抑制作用,并能高精度逼近非连续函数。Based on the approximation theory of Fourier-series working in square integrable space, a Fourier neuronal network was constructed by using activation functions of the complex exponential form. Then a weights-direct-determination method was derived to decide the neural-network weights immediately, which remedied the weaknesses of conventional BP neural networks such as small convergence rate, easily converging to local minimum and possibly lengthy or oscillatory learning process. A hidden-neurons-growing algorithm was presented to adjust the neural-network structure adaptively. Theoretical analysis and simulation results substantiate further that the presented Fourier neural network and algorithm could have good properties of high-precision learning, noise-suppressing and discontinuous-function approximating.

关 键 词：FOURIER级数 前向神经网络 权值直接确定 衍生算法 复指数 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]