摘要
针对基于传统梯度下降算法的前馈神经网络盲均衡在输入线性相关条件下收敛速度慢的问题,提出了一种修正解相关前馈神经网络盲均衡改进算法。对接收观测数据进行解相关处理,使梯度方向保持正交,同时,设定判断阈值,如果前馈神经网络输入相关系数大于阈值,说明输入向量强相关,保持梯度更新大小和方向不变,以克服强相关输入条件下解相关算法收敛停滞的问题。计算机仿真结果表明,文中提出的算法与基于直接梯度下降算法和传统解相关前馈神经网络盲均衡算法相比具有更快的收敛速度,有效提高了均衡性能。
To solve the problem of slow convergence rate in blind equalization by feedforward neural network（FNN）,a modified decorrelation algorithm is proposed and combined with FNN to implement blind equalization.In the algorithm the gradient vector can keep orthogonally by decorrelating to the input signals.Meanwhile,we set a threshold value to the correlate coefficient.If the correlate coefficient of input signals of FNN is bigger than threshold value,then the updating gradient value is kept for overcoming the stagnate of decorrelation algorithm for input signals.Computer simulation shows the effectiveness of the method proposed in this paper.
出处
《大连民族学院学报》
CAS
2012年第5期460-462,501,共4页
Journal of Dalian Nationalities University
基金
中央高校基本科研业务费专项资金资助项目(DC12010311)
辽宁省教育厅科学技术研究项目(2010046)
关键词
前馈神经网络
盲均衡
解相关
梯度下降算法
feedforward neural network
blind equalization
decorrelation
gradient descent algorithm
