Least squares estimation neural networks

Lately, there has been a great deal of interest in the use of artificial neural networks in many fields, including that of prediction and expert systems, and they are of interest here for the description of response surfaces that have a non-linear relation to the factor vari-ables. In such cases, the response surface may well fit the data better than that calculated from the model estimated by least-squares regression. " ... 

Harding, Popelier, and co-workers [285,286] have employed a variety of quantum chemical approaches in their estimation of the pK s ol oxyacids. In a study of 228 carboxylic acids they used what they call quantum chemical topology to find pK estimates. They tested several different methods, including partial least squares (PLS), support vector machines (SVMs), and radial basis function neural networks (RBFNNs) with Hartree-Fock and density functional calculations, concluding that the SVM models with HF/6-31G calculations were most efficient [285]. Foi a data set of 171 phenols they found that the C-0 bond length provided an effective descriptor for pK estimation [286]. 

---