One essential design factor for evaluating the performance of flexible pavement is the asphalt dynamic modulus (E*) of the logarithmic scale of dynamic modulus (log E*). Therefore, the current study aims to find a suitable model for predicting log E*. Thus, recurrent neural network (RNN), Radial basis function (RBF), Cascade Forward Neural Network (CFNN), and feedforward-backpropagation neural network (FBNN) were developed using data collected from NCHRP Report-547. The findings demonstrated that, in comparison to other models, the RNN model performs better, with R2 = 0.9826 for the validation phase. Additionally, the RSME and MAE show that, in terms of statistical parameters, the observed values and the obtained values of the RSM model closely agree with them.