| 一种带非线性扩展的前向神经网络模型及其学习算法 |
| |
| 引用本文： | 刘百顺,徐玉如,解贵新,刘学敏. 一种带非线性扩展的前向神经网络模型及其学习算法[J]. 哈尔滨工程大学学报, 1999, 20(3): 1-6 |
| |
| 作者姓名： | 刘百顺 徐玉如 解贵新 刘学敏 |
| |
| 作者单位： | 哈尔滨工程大学船舶与海洋工程系黑龙江哈尔滨150001 |
| |
| 摘 要： | 通过提出一种带非线性扩展的前向神经网络模型，分析了ＧＧＢＰ算法的收敛性，总结出此种算法的动态学习率。仿真结果表明：此神经网络模型更适合于处理多输入，多输出的问题，在这方面其收敛速度，逼近非线性函数的能力比函数型连接网络和前向网络都优越，采用动态学习不仅可以保证网络的收敛性，而且可以使误差下降接近最快。
|
| 关 键 词： | 神经网络 收敛性 动态学习率 |
| 文章编号： | 1006-7043(1999)03-0001-06 |
| 修稿时间： | 1998-10-13 |
A Multilayer Feedforward Network Model of Inputs with Nonlinear Function and Its Algorithm |
| |
| LIU Bai_shun,XU Yu_ru,XIE Gui_xin,LIU Xue_min. A Multilayer Feedforward Network Model of Inputs with Nonlinear Function and Its Algorithm[J]. Journal of Harbin Engineering University, 1999, 20(3): 1-6 |
| |
| Authors: | LIU Bai_shun XU Yu_ru XIE Gui_xin LIU Xue_min |
| |
| Abstract: | This paper develops a multilayer feedforward network model of inputs with nonlinear function, analyzes the convergence of the GGBP algorithm, generalizes the dynamical learning rate of the GGBP algorithm. The simulation results show : This network model much suitably deals with the problem of many inputs and many outputs; in this aspect, its convergence and capability of approximating the nonlinear function is better than the functional connection network and feedforward network. The dynamical learning rate not only ensures the convergence but also makes the error decrease nearly most rapidly. |
| |
| Keywords: | neural network convergence dynamical learning rate |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
