Context-dependent time-series prediction via HyperReservoirs
It is found that the HyperReservoir achieves the lowest mean test error in all three tasks, and particularly outperforms conceptors on data that is sampled from the same attractor but at different time scales, and particularly outperforms conceptors on data that is sampled from the same attractor but at different time...
K. Tsuchiyama, Takatomo Mihana, R. Horisaki et al.
· 0 citations