Polynomial neural network for linear and non-linear model selection in quantitative-structure activity relationship studies on the internet

This article presents a self-organising multilayered iterative algorithm th at provides linear and non-linear polynomial regression models thus allowin g the user to control the number and the power of the terms in the models. The accuracy of the algorithm is compared to the partial least squares (PLS ) algorithm using fourteen data sets in quantitative-structure activity rel ationship studies. The calculated data show that the proposed method is abl e to select simple models characterized by a high prediction ability and th us provides a considerable interest in quantitative-structure activity rela tionship studies. The software is developed using client-server protocol (J ava and C++ languages) and is available for world-wide users on the Web sit e of the authors.