Abstract: The Neural Network (NN) is an alternative to regression analysis for system modeling. It is a set of nonlinear equations used to predict output variable(s) from input variable(s) in a flexible way using layers of linear regressions and S-shape functions. The purpose of this study was to evaluate the fitness of the NN model to 2 sets of empirical weekly data obtained from first and second cycle of egg production. The goodness of fits for the obtained NN model were calculated by R2 value, adjusted R2, Mean Square Error (MSE), Residual Standard Error (RSE), Mean Absolute Percentage Error (MAPE) and the bias. The NN model adjusted R2 for first and second cycle of egg production were 0.999 and 0.998, respectively. These very high adjusted R2 revealed that the NN model is a better fit than those previously reported by the estimated regression models. It is concluded that the NN model may provide an effective mean to draw the pattern of egg production during the first and second cycle.
H. Ahmadi and A. Golian , 2008. Neural Network Model for Egg Production Curve. Journal of Animal and Veterinary Advances, 7: 1168-1170.