Stacked Heterogeneous Neural Networks for Time Series Forecasting

Table 4

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

		MSE on original data	MSE on normalized data
Training	Normal NN	66,484.341	$1.375\times {10}^{-3}$
	Exponential NN	88,404.178	$1.829\times {10}^{-3}$
	Stack	66,426.519	$1.374\times {10}^{-3}$
Testing	Normal NN	283,132.166	$5.858\times {10}^{-3}$
	Exponential NN	421,951.130	$8.730\times {10}^{-3}$
	Stack	283,105.757	$5.857\times {10}^{-3}$