Premium
A symbolic interpretation for back‐propagation networks
Author(s) -
Magrez P.,
Rousseau A.
Publication year - 1992
Publication title -
international journal of intelligent systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.291
H-Index - 87
eISSN - 1098-111X
pISSN - 0884-8173
DOI - 10.1002/int.4550070404
Subject(s) - interpretation (philosophy) , computer science , artificial intelligence , natural language processing , theoretical computer science , programming language
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 backpropagation 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.