Quoy M., “Structure and dynamics of random recurrent neural networks”, submitted

Abstract. In contradiction with Hopeld-like networks, random recur-rent neural networks (RRNN), where the couplings are random, exhibit complex dynamics (limit cycles, chaos). It is possible to store informa-tion in these networks through hebbian learning. Eventually, learning destroys the dynamics and leads to a xed point attractor. We inves-tigate here the structural change in the networks through learning, and show a small-world eect.