In this paper a natural gradient approach to blind source separation in complex environment is presented. It is shown that signals can be successfully reconstructed by a network based on the so called generalized splitting activation function (GSAF). This activation function, whose shape is modified during the learning process, is based on a couple of bi-dimensional spline functions, one for the real and one for the imaginary part of the input, thus avoiding the restriction due to the Louiville's theorem. In addition recent learning metrics are compared with the classical ones in order to improve the speed convergence. Several experimental results are shown to demonstrate the effectiveness of the proposed method. © 2009 IOS Press. All rights reserved.
A flexible natural gradient approach to blind separation of complex signals / Scarpiniti, Michele; D., Vigliano; Parisi, Raffaele; Uncini, Aurelio. - 193:1(2009), pp. 89-98. - FRONTIERS IN ARTIFICIAL INTELLIGENCE AND APPLICATIONS. [10.3233/978-1-58603-984-4-89].
A flexible natural gradient approach to blind separation of complex signals
SCARPINITI, MICHELE;PARISI, Raffaele;UNCINI, Aurelio
2009
Abstract
In this paper a natural gradient approach to blind source separation in complex environment is presented. It is shown that signals can be successfully reconstructed by a network based on the so called generalized splitting activation function (GSAF). This activation function, whose shape is modified during the learning process, is based on a couple of bi-dimensional spline functions, one for the real and one for the imaginary part of the input, thus avoiding the restriction due to the Louiville's theorem. In addition recent learning metrics are compared with the classical ones in order to improve the speed convergence. Several experimental results are shown to demonstrate the effectiveness of the proposed method. © 2009 IOS Press. All rights reserved.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.