Communication channel equalisation using minimal radial basis function neural networks

Results of nonlinear channel equalisation problems in data communications using a recently developed minimal radial basis function neural network structure, minimal resource allocation network (MRAN), are presented. A parsimonious network structure is ensured by the MRAN algorithm which uses online learning and has the capability to grow and prune the RBF network´s hidden neurons. Compared to earlier methods, the proposed scheme does not have to estimate the channel order first, and fix the model parameters. Results showing the superior performance of the MRAN algorithm for a linear channel equalisation problem, along with a nonlinear channel problem, are presented