Tutorial on Neural Networks Using the Broyden-Fletcher-Goldfarb - Shanno (BFGS) Training Algorithm and Molecular Descriptors with Application to the Prediction of Dielectric Constants through the Development of Quantitative Structure Property Relationships (QSPRs)

摘要

The use of quantitative structure property relationships (QSPRs) is proposed for the calculation of dielectric constants. A data set of 497 compounds with a wide variety of functional groups is assembled. These compounds span the dielectric constant range of 1-40. A total of 65 molecular descriptors is calculated for these compounds. These descriptors include the dipole moment, polarizability, counts of elemental types, an mediator of hydrogen bonding capability, charged partial surface area descriptors, and molecular connectivity descriptors. Subsets of these descriptors are used to build models in an attempt to find the best possible correlation between chemical structure and dielectric constant. A total of 70,000 models is examined. Neural networks using the Broyden-Fletcher-Goldfarb-Shanno (BFGS) training algorithm are employed to build the models. A total of 191 models has test set errors less than 2.0 and training set errors less than 3.0, where the errors are calculated as the mean of the absolute values of the residuals for sets of 97 and 350 compounds, respectively.