Evolutionary learning of small networks

Results are presented of a simulation which mimics an evolutionary learning process for small networks. Special features of these networks include a high recurrency, a transition function which decreases for large input activities, and the absence of tunable weights attached to the lines the line is either there (weight 1) or absent (weight 0). It is remarkable that already these simple systems exhibit a complex learning behavior and the phenomenon of punctuated equilibrium in the evolutionary process. These findings should be of interest for both, the general understanding of evolutionary dynamics and, more specifically, the understanding of the role of recurrence in combination with non-monotic response patterns for learning processes.