If much remains still to discover concerning animal brain?s internal structure as well as concerning its learning and self-organization mechanisms,, a number of recent advances in "neurobiology" already highlight some of key mechanisms of this marvels machine. Among them one can emphasizes brain?s "modular" structure and its "self-organizing" capabilities. The main goal of this paper is to show how these primary supplies, especially the modularity, could be exploited and combined in the frame of "soft-computing" issued techniques in order to design intelligent artificial systems emerging higher level intelligent behavior than conventional Artificial Neural Networks (ANN) based structures.