In this research a thin-layer drying kinetics of Asian pears (pyrus serotina rehd) during microwave drying with three slice thicknesses (2, 4, and 6 mm) and three level of microwave powers (200, 300, and 400 W) were studied. Increasing microwave power and decreasing slice thickness caused to decrease drying time. Drying time measured values were compared with predicted values obtained from mathematical and artificial neural networks (ANN) models. Ten thin-layer drying models were fitted to the drying experiments in the range of the employed slice thickness and microwave power values. The drying model assessment revealed that the Logarithmic model exhibited the best performance in fitting the experimental data (R²=0.9948, RMSE= 0.2013 and SSE=0.01135). Using some of the experimental data, an ANN was developed to predict moisture ratio (MR) and drying rate (DR) values based on the three input variables (time, thickness and power). Multi layer perceptron network (MLP) was used for nonlinear mapping between the input and the output parameters. After evaluation of different trains, the optimal model was a three-layered back-propagation ANN, with 20 neurons in the hidden layer. The ANN model was able to predict the moisture ratio and drying rate quite well with determination coefficients (R²) of 0.99563.