Diversifying non-dissipative Reservoir Computing dynamics

The Euler State Network (EuSNs) model is a recently proposed Reservoir Computing methodology that provides stable and non- dissipative untrained dynamics by discretizing an appropriately con-strained ODE. In this paper, we propose alternative formulations of the reservoirs for EuSNs, aiming at improving the diversity of the resulting dynamics. Our empirical analysis points out the effectiveness of the proposed approaches on a large pool of time-series classification tasks.