Stacked Heterogeneous Neural Networks for Time Series Forecasting

Table 2

The errors of the model for the sunspot data (window size 10).

		MSE on original data	MSE on normalized data
Training	Normal NN	96.085	$2.656\times {10}^{-3}$
	Exponential NN	811.737	$22.438\times {10}^{-3}$
	Stack	96.085	$2.656\times {10}^{-3}$
Testing	Normal NN	619.387	$17.121\times {10}^{-3}$
	Exponential NN	2466.148	$68.170\times {10}^{-3}$
	Stack	619.387	$17.121\times {10}^{-3}$