Prediction of phenolic compounds and glucose content from dilute inorganic acid pretreatment of lignocellulosic biomass using artificial neural network modeling

Bioresources and Bioprocessing

Table 2 Computational results of RMSE during the training and validation processes with different neurons of hidden layer in ANN models. RMSE is the root means square error calculated by Eq. (3)

Neurons in hidden layer, n	RMSE for C_Glc after 500 iterations		RMSE for C_Phe after 500 iterations
Neurons in hidden layer, n	Training dataset	Validation dataset	Training dataset	Validation dataset
n = 3	7.16	7.12	0.54	0.41
n = 4	9.35	8.51	0.87	0.42
n = 5	7.92	6.06	0.56	0.18
n = 6	6.71	6.41	1.37	1.05
n = 7	6.44	5.47	0.46	0.22
n = 8	7.53	5.84	0.46	0.46
n = 9	6.41	5.03	0.42	0.40
n = 10	6.40	5.20	0.43	0.28
n = 11	6.57	4.97	0.53	0.25
n = 12	6.38	4.73	0.43	0.24
n = 13	6.50	5.46	0.43	0.32