Structured reservoir computing with spatiotemporal chaotic attractors.
Carlos Lourenço · 2007
Abstract. We approach the themes “computing with chaos ” and “reservoir computing ” in a unified setting. Different neural architectures are mentioned which display chaotic as well as reservoir properties. The architectures share a common topology of close-neighbor connections which supports different types of spatiotemporal dynamics in continuous time. We bring up the role of spatiotemporal structure and associated symmetries in reservoir-mediated pattern processing. Such type of computing is somewhat different from most other examples of reservoir computing. 1 Spatiotemporal chaotic reservoirs Previously we have described the reservoir property in the context of chaotic dynamical systems and pointed out that it is a useful manifestation of chaos’ flexibility in view of computation [1, 2, 3, 4]. The recent developments in reservoir computing research [5, 6, 7] prompted us to recall some of the previous ideas concerning computing with dynamical networks, as well as to provide new results and suggest research directions. Our work aims at classifying arbitrarily