Table 3.

(L96) Details of comparing all three methods at 32 bits of precision where the divergence time in the last column is the main point of conclusion.

	training error	TF error	SF error	divergence time
LSR-ESN	1.80 × 10−4	4.32 × 10−2 ± 1.75 × 10−3	1.18 ± 9.81 × 10−2	1.24 ± 4.74 × 10−1
HSR-ESN	7.07 × 10−5	4.08 × 10−1 ± 3.37 × 10−1	1.09 × 101 ± 8.61	4.53 × 10−1 ± 5.93 × 10−1
D2R2	2.24 × 10−4	2.28 × 10−4 ± 2.11 × 10−5	1.14 ± 1.06 × 10−1	1.60 ± 5.31 × 10−1