What makes a dynamical system computationally powerful?

R. Legenstein and W. Maass

Abstract:

We review methods for estimating the computational capability of a complex dynamical system. The main examples that we discuss are models for cortical neural microcircuits with varying degrees of biological accuracy, in the context of online computations on complex input streams. We address in particular the question to what extent earlier results ab out the relationship between the edge of chaos and the compu tational power of dynamical systems in discrete time for off -line computing also apply to this case.



Reference: R. Legenstein and W. Maass. What makes a dynamical system computationally powerful? In S. Haykin, J. C. Principe, T. Sejnowski, and J. McWhirter, editors, New Directions in Statistical Signal Processing: From Systems to Brains, pages 127-154. MIT Press, 2007.