An ensemble learning algorithm for blind signal separation problem

The framework in Bayesian learning algorithms is based on the assumptions that the quantities of interest are governed by probability distributions, and that optimal decisions can be made by reasoning about these probabilities together with the data. In this paper, a Bayesian ensemble learning approach based on enhanced least square backpropagation (LSB) neural network training algorithm is proposed for blind signal separation problem. The method uses a three layer neural network with an enhanced LSB training algorithm to model the unknown blind mixing system. Ensemble learning is applied to estimate the parametric approximation of the posterior, probability density function (pdf). The Kullback-Leibler information divergence is used as the cost function in the paper. The experimental results on both artificial data and real recordings demonstrate that the proposed algorithm can separate blind signals very well.