作者: R.A. Kennedy , B.D.O. Anderson , Z. Ding , C.R. Johnson
关键词:
摘要: A common recursive identification scheme used in a class of adaptive systems problems involving blind channel equalization (but potentially usable elsewhere) is an algorithm due to Sato. The authors study the convergence properties Sato by characterizing mean cost surface. results show important feature that equalizer parameters may converge parameter settings which fail achieve ideal objective approximate inverse with sufficient accuracy. proof well-posed can misbehave presented. Examples are illustrate results. >