摘要
本文提出了一种复数赫布类型的学习算法，用来训练一个输入、输出及权值均为复数的复神经网络．本算法的推导是基于ＴＬＳ准则，而不是常用的ＬＳ或ＬＭＳ准则．算法的收敛性及收敛结果通过将其应用到自适应复数ⅡＲ滤波器中来加以说明．
In this brief paper, a Complex Hebbian-type learning algorithm for training a complex neural net work whose inputs, outputs and weights are all complex was proposed. We derive thealgorithm in TLS sense other than in LS or LMS sense. The performance of the proposed algorithm is demonstrated with application in complex adaptive IIR filtering
出处
《信号处理》
CSCD
2000年第4期332-337,共6页
Journal of Signal Processing
