Wave propagation as a neural coupling mechanism: hardware for self-organizing feature maps and the representation of temporal sequences

Wave propagation within a “cortex” of neurons is introduced as a neural coupling mechanism. Using this effect for the control of the neural learning process, the network generates self-organizing feature maps. Additionally, wave propagation is used to influence the neural competition in representing the input of the network. By this means the network is able to represent temporal aspects of the input. Since apart from a global bus such a network only requires local interactions, connectivity is very low and a parallel hardware implementation suggests itself. Operation of a demonstration setup consisting of 16 neurons in digital technology is demonstrated by the representation of phoneme sequences