| 联想神经网络异步工作方式下收敛性能的研究 |
| |
| 引用本文： | 史玉回,何振亚.联想神经网络异步工作方式下收敛性能的研究[J].信号处理,1993(2). |
| |
| 作者姓名： | 史玉回 何振亚 |
| |
| 作者单位： | 东南大学无线电工程系，东南大学无线电工程系 |
| |
| 摘 要： | 本文对具有投影学习算法的Hopfield型二值神经网络在异步工作方式下收敛性能进行了比较全面的分析讨论,采用非能量函数的方法证明了网络具有演化收敛到网络平衡点的特性;推导了计算网络收敛所需瞬态工作步数上界的估算公式;分析并给出了计算平衡点(记忆模式)收敛半径的算法.
|
| 关 键 词： | 联想神经网络 直交投影算子 收敛性 收敛半径 |
STUDY ON CONVERGENT PROPERTIES OF ASSOCLATIVE NEURAL NETWORK UNDER ASYNCHRONOUS UPDATING OPERATION |
| |
| Shi Yuhui He Zhenya.STUDY ON CONVERGENT PROPERTIES OF ASSOCLATIVE NEURAL NETWORK UNDER ASYNCHRONOUS UPDATING OPERATION[J].Signal Processing,1993(2). |
| |
| Authors: | Shi Yuhui He Zhenya |
| |
| Abstract: | In this paper, the convergent properties of Hopfield-type associative neural network with projectlearning rule under asynchronous update operation has been studied. Using non-energy function method, we haveproved the network having the property converging to one of its equilibrium points. A formula for estimatingthe upper bound of update steps required for convergence and a algorithm for calculating the convergent radius ofthe equilibrium point have been derived. |
| |
| Keywords: | Associative neural network Orthogonal projector Convergence Convergent radius |
| 本文献已被 CNKI 等数据库收录！ |
