Fig. 1From: CPANNatNIC software for counter-propagation neural network to assist in read-acrossA scheme of counter-propagation neural network. An input object (vector of X values—descriptors) with descriptors (top-left) and endpoint values (bottom-left). CPANN scheme is shown on the right. Kohonen layer is on the top and the output layer with three response levels used to draw response surfaces is below the Kohonen layerBack to article page