Recently several papers have been published on nonlinear prediction applied to speech coding. At ICASSP98 we presented a system based on an ADPCM scheme with a nonlinear predictor based on a neural net. The most critical parameter was the training procedure in order to achieve good generalization capability and robustness against mismatch between training and testing conditions. In this paper, we propose several new approaches that improve the performance of the original system in up to 1.2dB of SEGSNR (using bayesian regularization). The variance of the SEGSNR between frames is also minimized, so the new scheme produces a more stable quality of the output.