Robustness and convergence of adaptive schemes in blind equalization and neural network training

Sayed, Ali H.Rupp, Markus2017-12-192017-12-192017-12-191996https://infoscience.epfl.ch/handle/20.500.14299/143305We pursue a time-domain feedback analysis of adaptive schemes with nonlinear update relations. We consider commonly used algorithms in blind equalization and neural network training and study their performance in a purely deterministic framework. The derivation employs insights from system theory and feedback analysis, and it clarifies the combined effects of the step-size parameters and the nature of the nonlinear functionals on the convergence and robustness performance of the adaptive schemes.Robustness and convergence of adaptive schemes in blind equalization and neural network trainingtext::conference output::conference proceedings::conference paper