Nonlinear blind signal separation: an RBF-based network approach

This paper presents a radial basis function (RBF) based approach for blind signal separation in a nonlinear mixture. A cost function, which consists of the mutual information and partial moments of the outputs of the separation system, is defined to extract the independent signals from their nonlinear mixtures. The minimization of the cost function results in the independence of the outputs with desirable moments such that the original sources are separated properly. A learning algorithm for the parametric RBF network is established by using the stochastic gradient descent method. This approach is characterized by high learning convergence rate of weights, modular structure, as well as feasible hardware implementation. A simulation result demonstrates the feasibility, and validity of the proposed approach.