par Magrez, Paul ;Rousseau, A.
Référence International journal of intelligent systems, 7, 4, page (339-360)
Publication Publié, 1992-06
Référence International journal of intelligent systems, 7, 4, page (339-360)
Publication Publié, 1992-06
Article révisé par les pairs
Résumé : | Two main problems for the neural network (NN) paradigm are discussed: the output value interpretation and the symbolic content of the connection matrix. In this article, we construct a solution for a very common architecture of pattern associators: the back-propagation networks. First, we show how Zadeh's possibility theory brings a formal structure to the output interpretation. Properties and practical applications of this theory are developed. Second, a symbolic interpretation for the connection matrix is proposed by designing of an algorithm. By accepting the NN training examples as input this algorithm produces a set of implication rules. These rules accurately model the NN behavior. Moreover, they allow to understand it, especially in the cases of generalization or interference. |