ADAPTATION BASED ON MEMORY DYNAMICS IN A CHAOTIC NEURAL NETWORK
Nigel T. Crook, Tjeerd V. olde Scheper · Cybernetics & Systems · 2002
The complex dynamics that emerge from systems governed by deterministic chaos offer significant advantages to the neuromorphic engineer. Included in these is the potential for a very large memory store and the ease with which chaotic systems can be controlled. By definition, a chaotic system is a periodic. However, during the course of its trajectory through state space, the chaotic system will come infinitely close to points that it has previously visited. These almost repeating trajectories are referred to as Unstable Periodic Orbits (UPOs). Normally, under the influence of chaos, the trajectory would move away exponentially fast from its previous path, thereby describing a new path on the surface of the attractor. It is possible to apply a simple delayed feedback control mechanism to a chaotic system that will constrain it within one of its UPOs. This article presents a neural implementation of this delayed feedback mechanism. The network presented here is able to stabilize different UPOs in response to different input signals, with each UPO corresponding to a dynamic recognition state for that input. We also present two learning rules for this network, which enables it to adapt to novel inputs in a self-organized manner.