Rational Function Functional Networks Based on Function Approximation

In order to solve function approximation, a mathematic model of Rational Function Functional Networks (RFFN) based on approximation was proposed and the learning algorithm for function approximation was presented. This algorithm used the lease square method thought and constructed auxiliary function by Lagrange multiplier method, and the parameters of the rational function functional networks were determined by solving a system of linear equations. Results illustrate the effectiveness of the rational function functional networks in solving approximation problems of the function with a pole.