Drilling costs and time are directly affected by the rate of penetration (ROP). Gas/oil well drilling in challenging environments is a costly operation due to the high cost of wellbore construction, and drilling optimization requires real-time decision-making. Therefore, it is necessary to estimate ROP accurately and thus assist in optimizing the drilling process. In this study, we used total depth, weight on hook, bit, revolutions per minute, torque, standpipe pressure, flow rates, mud weight, mud viscosity, hole size, and formation hardness as input parameters to forecast ROP. Nine machine learning algorithms, i.e., multiple linear regression (MLR), lasso regression, ridge regression, decision tree (DT), bootstrap aggregating (Bagging), random forest (RF), gradient boosting machines (GBM), symbolic regression (SR), and artificial neural networks (ANN) were performed using a dataset consists of 3484 observations. Moreover, several network hyperparameters were adjusted, indicating that using a deep artificial feed-forward network, i.e., [9-11-1] neurons with logarithmic sigmoid transfer function as a predictor model, provided the most accurate model. Results showed that the random forest and artificial neural network models have the highest accuracy, and it estimates ROP with correlation coefficients of 0.93. Overall, the methodology employed in this paper performed well in predicting ROP in the absence of some unavailable parameters such as UCS.