Stacked Heterogeneous Neural Networks for Time Series Forecasting

Table 10

The errors of the model for the super-exponential growth data (window size 10).

		MSE on original data	MSE on normalized data
Training	Normal NN	5.270	$12.651\times {10}^{-5}$
	Exponential NN	1.047	$2.513\times {10}^{-5}$
	Stack	1.047	$2.513\times {10}^{-5}$
Testing	Normal NN	939.119	$22.544\times {10}^{-3}$
	Exponential NN	76.707	$1.841\times {10}^{-3}$
	Stack	76.707	$1.841\times {10}^{-3}$