Novel FTLRNN with Gamma Memory for Short-Term and Long-Term Predictions of Chaotic Time Series

Table 4

Learning rules variations for the real sunspots and Laser time series.

Learning rule	Real sunspots time series			Real Laser time series
	(𝐾=6 months ahead prediction)			(𝐾=10 step ahead prediction)
	MSE	NMSE	𝑟	MSE	NMSE	𝑟
Conjugate gradient	0.00624	0.1135	0.9450	0.1450	0.511140	0.79772
Momentum	0.00554	0.1008	0.95528	0.009563	0.337	0.8302
Quick Propagation	0.00866	0.15757	0.92256	0.01787	0.62995	0.64371