This work addresses the prediction of dynamic viscosities of several fatty acid esters and biodiesel fuels using a semi-theoretical model and artificial neural network as well. The semi-theoretical model used rough hard-sphere theory for the correlation and prediction of dynamic viscosities. In this respect, a smooth hard-sphere-chain expression and a coupling parameter of translational-rotational motions were employed to develop the rough hard-sphere-chain scheme. The three molecular parameters as well as the liquid densities required in this model were taken from previously developed perturbed Yukawa-chain equation of state (Fluid Phase Equilibria, 372 (2014) 105-112). Artificial neural network modeling employed a multilayer perceptron comprising one hidden layer and 21 neurons, managed according to the constructive approach. The performance of both semi-theoretical and ANN model have been checked by predicting dynamic viscosities over the temperature range within 283-393 K and pressures up to 140 MPa with the average absolute relative deviation of 3.10% (for 648 data points) and 0.91% (for 796 data points), respectively. The ANN model developed herein, has been trained, validated and tested for the set of data gathered, pointing that the efficiency of the neural network model was found excellent on the entire dataset.