卡尔曼滤波器
计算机科学
梯度下降
控制理论(社会学)
趋同(经济学)
收敛速度
均衡(音频)
盲均衡
扩展卡尔曼滤波器
人工神经网络
算法
快速卡尔曼滤波
频道(广播)
自适应滤波器
不变扩展卡尔曼滤波器
人工智能
电信
经济
经济增长
控制(管理)
作者
Ren-Cheng Huang,Mu‐Song Chen
标识
DOI:10.1109/icosp.2000.894544
摘要
In this paper, a complex-valued neural network based on the Kalman filter is presented for channel equalization in a communication system. The complex-valued decoupled extended Kalman filter algorithm is derived which provides a faster convergence rate and better performance than those of complex back-propagation algorithms. Computer simulation results showed that the proposed scheme has a faster convergence behavior and smaller signal constellation than the gradient descent based learning algorithm via the linear and nonlinear channel equalization problem.
科研通智能强力驱动
Strongly Powered by AbleSci AI