An adaptive chaotic neural network

The non-linear dynamics of a chaotic attractor offer a number of useful features to the developer of neuromorphic systems. Included in these is the ability for efficient memory storage and recall. A chaotic attractor has a potentially infinite number of unstable periodic orbits (UPO) embedded within it. These orbits can be stabilised with the application of delayed feedback inhibition. This research investigates the possibility of using such delayed feedback in a network to stabilise different UPOs in response to disparate input stimuli. A key feature of the models presented is that the UPOs, which correspond to dynamic memory states, emerge from the dynamics of the attractor. The paper presents two learning rules which support the network dynamics from which the memory states emerge