Journal of Computer Applications
• Artificial intelligence • Previous Articles Next Articles
Yu-Nong Zhang Qing-Dan Zeng Xiu-Chun Xiao Xiao-Hua Jiang A-Jin Zou
Received:
Revised:
Online:
Published:
Contact:
张雨浓 曾庆淡 肖秀春 姜孝华 邹阿金
通讯作者:
Abstract: 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 weightsdirectdetermination method was derived to decide the neuralnetwork 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.
Key words: Fourier series, weights-direct-determination, feed-forward neural network, growing algorithm, complex-exponent
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。
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
Yu-Nong Zhang Qing-Dan Zeng Xiu-Chun Xiao Xiao-Hua Jiang A-Jin Zou. Complex-exponential Fourier neuronal networkand its hidden-neuron growing algorithm[J]. Journal of Computer Applications.
张雨浓 曾庆淡 肖秀春 姜孝华 邹阿金. 复指数Fourier神经元网络隐神经元衍生算法[J]. 计算机应用.
0 / Recommend
Add to citation manager EndNote|Ris|BibTeX
URL: http://www.joca.cn/EN/
http://www.joca.cn/EN/Y2008/V28/I10/2503