Response to “Comment on a recent sensitivity analysis of radial base function and multi-layer feed-forward neural network models”

In our paper [1], the modeling capabilities of multi-layered feed-forward (MLF) and radial base function (RBF) networks were investigated on simulated data and well described experimental data from chemical industry [4]. Since both networks are based on a different concept (that is, RBF in contrast to MLF shows more local modeling behaviour) both modeling capability and robustness to input errors have been examined. The ‘robustness’ was expressed in terms of sensitivity of the network output units to random input perturbations by means of controlled pseudo-random noise. In this response paper, the comment of Faber et al., i.e., applying theoretical error propagation on artificial neural networks, and the consequences for the conclusions drawn in the original paper [1], are addressed.