首页 | 本学科首页   官方微博 | 高级检索  
     

基本样条循环神经网络及其非线性建模
引用本文:金宏 张洪钱. 基本样条循环神经网络及其非线性建模[J]. 控制与决策, 1999, 14(5): 469-472
作者姓名:金宏 张洪钱
作者单位:[1]北京航空航天大学自动控制系 [2]北京航空航天大学
摘    要:提出一种新的基于基本样条逼近的循环神经网络,该网络易于训练且收敛速度快。此外为克服定长学习步长训练速度慢的问题,提出一种用于该网络训练的自适应权值更新算法,给出了学习步长的最优估计。该最优学习步长的选择可用于基本样条循环神经网络的训练以及对非线性系统的建模。

关 键 词:循环神经网络 基本样条 非线性建模 BSRNN

B-Spline Recurrent Neural Network and Its Nonlinear Modelling
Jin Hong. B-Spline Recurrent Neural Network and Its Nonlinear Modelling[J]. Control and Decision, 1999, 14(5): 469-472
Authors:Jin Hong
Affiliation:Jin Hong(Beijing University of Aeronautics and Astronautics) C W Chan(University of Hongkong) Zhang Hongyue(Beijing University of Aeronautics and Astronautics)
Abstract:A new recurrent neural network based on B-spline function approximation is presented. The network can be easily trained and its training converges more quickly. Moreover, in order to overcome the slowness of training caused by constant learning rate, an adaptive weight updating algorithm used for training the recurrent network is proposed and an optimal estimate of learning rate is given. Examples are given to show that the optimal learning rate can be used to train the B-spline recurrent neural network, and this recurrent neural network can be applied to modelling of a nonlinear dynamic system.
Keywords:recurrent neural network   B-spline function   adaptive learning algorithm   optimal learning rate
本文献已被 CNKI 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号