Simulation Study of Physical Reservoir Computing by Nonlinear Deterministic Time Series Analysis

We investigate dynamics of physical reservoir computing by numerical simulations. Our approach is based on nonlinear deterministic time series analysis such as Takens' theorem and false nearest neighbor methods. We show that this approach is useful for efficient design and implementation of physical reservoir computing systems where only partial information of the reservoir state is accessible. We take nonlinear laser dynamics subject to time delay as physical reservoir and show that the size of physical reservoir can be estimated by these method.