Training counterpropagation neural network

All of the algorithms described in this article have been based on an assembly of structural fragments. Recently, a new approach of 3D structure elucidation from infrared spectra by counterpropagation neural networks has been reported. Although the output structure depends on the training data set, the mechanism is quite different from the conventional method. This method is probably useful in cases where the solution space is restricted. The complementary use of both methods may open the door to new fields enhanced by structure generation. 

Several nonlinear QSAR methods have been proposed in recent years. Most of these methods are based on either ANN or machine learning techniques. Both back-propagation (BP-ANN) and counterpropagation (CP-ANN) neural networks [33] were used in these studies. Because optimization of many parameters is involved in these techniques, the speed of the analysis is relatively slow. More recently, Hirst reported a simple and fast nonlinear QSAR method in which the activity surface was generated from the activities of training set compounds based on some predefined mathematical functions [34]. 

M-CASE/BAIA (see text). BP-ANN = three-layer feedforward artificial neural network trained by the backpropagation algorithm, PAAN = probabilistic artificial neural network, CPANN = counterpropagation artificial neural network. 

Counterpropagation (CPG) Neural Networks are a type of ANN consisting of multiple layers (i.e., input, output, map) in which the hidden layer is a Kohonen neural network. This model eliminates the need for back-propagation, thereby reducing training time. 

---