The Dependence of Reservoir Computing on System Parameters

Reservoir computing (RC) has become an interesting topic for the nonlinear Dynamics field. More so because despite many demonstrations of RC abilities the actual dynamical reasons RCs work is still not well understood. We examined several aspects of RC using fitting and prediction of signals as a benchmark. Among the parameters we explored [1] were network heterogeneity of link weights, existence of symmetries in the networks, variations of node parameters and vector fields, and spectral radius of the network. One important result is that the number of independent signals that can be used from a driven RC is limited and independent of the number of nodes above a certain vertex number.

authors:
[1] Network Structure Effects in Reservoir Computers, T. L. Carroll and L. M. Pecora, CHAOS, Chaos 29, 083130 (2019)