Stacked Heterogeneous Neural Networks for Time Series Forecasting

Table 9

The errors of the model for the super-exponential growth data (window size 5).

		MSE on original data	MSE on normalized data
Training	Normal NN	2.825	$6.783\times {10}^{-5}$
	Exponential NN	1.593	$3.824\times {10}^{-5}$
	Stack	1.593	$3.824\times {10}^{-5}$
Testing	Normal NN	826.936	$19.851\times {10}^{-3}$
	Exponential NN	172.645	$4.144\times {10}^{-3}$
	Stack	172.645	$4.144\times {10}^{-3}$