Application of cascade-correlation neural networks to nonlinear system identification

Application of Cascade-Correlation Neural Networksto Nonlinear System IdentificationElectrical EngineeringMuch research in recent years has been done in applying artificial neural networksto the problem of nonlinear system identification. The most common neural network archi-tecture, the multilayer feed-forward network, trained with the backpropagation algorithm,has been shown to be capable of universal function approximation which makes it appli-cable to a much wider range of problems than other nonlinear identification techniques.While these neural networks show great potential, they still suffer several drawbacks, suchas slow convergence toward a solution. New neural network architectures have been pro-posed in an attempt to overcome these limitations. This study examines one such architec-ture, Cascade-Correlation, and its usefulness in system identification applications, particu-larly the nonlinear case.