Stacked Heterogeneous Neural Networks for Time Series Forecasting

Table 3

The errors of the model for the lynx data (window size 5).

		MSE on original data	MSE on normalized data
Training	Normal NN	530,416.473	$10.974\times {10}^{-3}$
	Exponential NN	383,963.211	$7.944\times {10}^{-3}$
	Stack	401,015.900	$8.297\times {10}^{-3}$
Testing	Normal NN	154,951.311	$3.206\times {10}^{-3}$
	Exponential NN	113,955.783	$2.357\times {10}^{-3}$
	Stack	109,902.034	$2.273\times {10}^{-3}$