Neural networks with orthogonalised transfer functions

Approximation capabilities of single non-linear layer networks, that feature a single global minimum of the error function are addressed. Bases of different transfer functions are tested (Gaussian, sigmoidal, multiquadratics). These functions are orthogonalised in an incremental manner for training and restored back to the original basis for network deployment. Approximation results are given for a benchmark ECG signal. Results of incremental training with basis orthogonalisation are also shown for 2D approximations.