1990 · 45 citations · 0 references
EngineeringComputer ScienceElectrical EngineeringDynamical SystemsInformation TheoryMachine LearningDigital Signal ProcessingNeural NetworksNeural OscillationsNeural Signal ProcessingSignal Detection TheorySignal ProcessingAdaptive EqualizationAdaptive Signal ProcessingEqualizationMean Absolute ErrorSelf-organizing MapsSelf-organizing Networks
An adaptive algorithm combining traditional linear equalization techniques and a self-organizing neural learning algorithm is presented. The results show that the performance of the neural equalizer is insensitive to nonlinear learning distortions in dynamic discrete-signal detection. Stabilization of the self-organizing map during undistorted transmission has to be further considered to decrease the absolute mean-square error (MSE) rate of the neural equalizer. The error is due to oscillations in the self-organizing map, mainly caused by the neighborhood learning. The oscillations can be decreased by taking more samples to the map before adapting the <e1 xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m</e1> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i</sub> values and by decreasing the neighborhood learning parameter β