Digital spike maps and learning of spike signals

This paper studies the digital spike map and its learning algorithm. The map can be regarded as a simple class of cellular automaton and can generate various digital spike-trains. The learning algorithm is simple and includes self-organizing function. Performing basic numerical experiments, we have clarified that the map can learn a typical class of teacher signals and the learned the digital spike map can output various digital spike-trains depending on the initial state. The results contribute to bridge between spiking neural systems and digital dynamical systems with rich applications.