Neural system of classification and classification method using such a

Abstract

The disclosure concerns neural networks designed specially for the classification of objects represented by vectors X. If the vectors X include several parameters and if the objects have to be classified in a large number N of classes, the end result is a very large number of interconnections which become difficult to set up physically, are slow in their operation and require lengthy learning phases. The disclosed neural classification system has the particular feature of being constituted on the basis of P neural networks each individually carrying out the classification of objects in only two classes or, at any rate, in a small number of classes only. These networks give probabilities P.sub.i,j of membership in a class C.sub.i among two classes C.sub.i and C.sub.j. The outputs of these networks are connected to a signal processing module which, through simple functions (implementing linear combinations of the outputs and non-linear standardization functions) establishes, on N outputs, results P.sub.i (X) of classification among the N classes. The learning is done on classifications by pairs of classes, but the post-learning recognition gives classifications among N classes.