This study was conducted to compare the responses of broiler chicks [average daily gain (ADG) and feed efficiency (FE)] of before and after 2000 to dietary protein and lysine through neural network (NN). The available lysine dose-response data were extracted from the literature and divided into two sets of before and after 2000. The training and testing data sets, derived from each group, were used to develop the NN models. The developed models were subjected to a sensitivity analysis test to assess the relative importance of dietary protein and lysine on chicks responses. The optimization algorithm were used to find the dietary protein and lysine required for maximum ADG and FE, based on either data sets. The results revealed that the developed NN models could efficiently predict the ADG and FE in broiler chicks of before and after 2000, and the higher accuracy of prediction were attained by these models as compared to the regression models. The sensitivity analysis indicated that the ADG and FE were more sensitive to dietary lysine, compared to protein in both time periods. Based on the optimization results, the protein requirement for maximum ADG or FE for birds reared after 2000 were lower, whereas the lysine requirement was higher as compared to those reared before 2000. The protein requirement for maximum ADG and FE for birds reared before 2000 were 241.3 and 247.0 (g/kg of diet) and for lysine 10.76 and 11.18 (g/kg of diet), respectively. In birds reared after 2000, maximum ADG was obtained when diet contained 224.30(g/kg of diet) protein and 11.75 (g/kg of diet) lysine, while the maximum FE was achieved with diet contained 228.3(g/kg of diet) protein and 13.1 (g/kg of diet) lysine.

Keywords