Supervised Neural Networks for the Classi cation of Structures

Until now neural networks have been used for classifying unstructured patterns and sequences. However, standard neural networks and statistical methods are usually believed to be inadequate when dealing with complex structures because of their feature-based approach. In fact, feature-based approaches usually fail to give satisfactory solutions because of the sensitivity of the approach to the a priori selection of the features, and the incapacity to represent any speciic information on the relationships among the components of the structures. However, we show that neural networks can, in fact, represent and classify structured patterns. The key idea underpinning our approach is the use of the so called \generalized recursive neuron", which is essentially a generalization to structures of a recurrent neuron. By using generalized recursive neurons, all the supervised networks developed for the classiication of sequences, such as Back-Propagation Through Time networks, Real-Time Recurrent networks, Simple Recurrent Networks, Recurrent Cascade Correlation networks, and Neural Trees can, on the whole, be generalized to structures. The results obtained by some of the above networks (with generalized recursive neurons) on the classiication of logic terms are presented.