Stochastic Gradient-Adaptive Complex-Valued Nonlinear Neural Adaptive Filters With a Gradient-Adaptive Step Size

@article{Goh2007StochasticGC,
  title={Stochastic Gradient-Adaptive Complex-Valued Nonlinear Neural Adaptive Filters With a Gradient-Adaptive Step Size},
  author={Su Lee Goh and Danilo P. Mandic},
  journal={IEEE Transactions on Neural Networks},
  year={2007},
  volume={18},
  pages={1511-1516}
}
A class of variable step-size learning algorithms for complex-valued nonlinear adaptive finite impulse response (FIR) filters is proposed. To achieve this, first a general complex-valued nonlinear gradient-descent (CNGD) algorithm with a fully complex nonlinear activation function is derived. To improve the convergence and robustness of CNGD, we further introduce a gradient-adaptive step size to give a class of variable step-size CNGD (VSCNGD) algorithms. The analysis and simulations show the… CONTINUE READING