AN APPLICATION OF NEURAL NETWORKS IN CHEMISTRY

Basic definitions of the N-layer neural network are given. Partial derivatives of the objective functions with respect to the weight and threshold coefficients are derived. These derivatives are valuable for an adaptation process of the considered neural network, the resulting optimal weight and threshold coefficients are used in the forthcoming active process. The neural network may be applied as a classifier of objects. The theory is illustrated by an application of three-layer neural network to the classification of C-13 NMR chemical shifts of acyclic alkanes.