Abstract
In this article we are going to discuss the improvement of the multi classes' classification problem using multi layer Perceptron. The considered approach consists in breaking down the n-class problem into two-classes' subproblems. The training of each two-class subproblem is made independently; as for the phase of test, we are going to confront a vector that we want to classify to all two classes' models, the elected class will be the strongest one that won't lose any competition with the other classes. Rates of recognition gotten with the multi class's approach by two-class's decomposition are clearly better that those gotten by the simple multi class's approach.