Predicting the growth performance of growing-finishing pigs based on net energy and digestible lysine intake using multiple regression and artificial neural networks models

Table 4 The performance of ANN models with different numbers of nodes and activation functions to predict the ADG of growing-finishing pigs¹

Number of nodes	Training data set
	Hyperbolic tangent function		Radial basis function
	R²	RMSE	R²	RMSE
1	0.921	75	0.918	77
2	0.932	70	0.936	68
3	0.942	64	0.941	65
4	0.941	65	0.964^*	51^*
5	0.952	59	0.958	55
6	0.948	61	0.955	57
7	0.948	61	0.952	58
8	0.942	65	0.945	63
9	0.944	63	0.951	59
10	0.953	58	0.953	58

RMSE root mean square error.
^* Means the best performance of ANN models with different numbers of nodes and activation functions to predict ADG.
¹ All the ANN models were generated using the training data set (n = 287).

ISSN: 2049-1891