DONATO JÚNIOR, E. T.; http://lattes.cnpq.br/6465859482633047; DONATO JÚNIOR, Edmundo Tojal.
Résumé:
The Combinatorial Neural Model (MNC) is a neural network of superior order
that is adequate to classification tasks. The training of this network is performed by
an algorithm based on backpropagation, through punishments and rewards, according
to the examples of the training set. This work detaches the importance of the
background knowledge to learning process in a general form and describes how
semantic relevance and attribute valoration can improve both the quality of learning
accomplished by MNC and the performance of the training algorithm. The presented
alterations actuate on the topology of the network to be trained and are compatible
with the extensions that have been proposed to the Model.