Steam-assisted gravity drainage (SAGD) is an enhanced oil recovery technology for heavy (or viscous) oil and bitumen that involves drilling two horizontal wells in underground formations. Laboratory work, pilot-plant studies, and mathematical model development, which are generally costly, difficult, and time-consuming tasks, are taken into account as important stages in finding an effective and economical method and also predicting the performance of the SAGD technique for a certain heavy-oil reservoir. Currently, smart techniques as accurate and fairly fast tools are highly recommended for these purposes. In this work, an experimental study and an artificial neural network (ANN) linked to an optimization technique, called particle swarm optimization (PSO), were employed to obtain performance parameters such as the cumulative steam-to-oil ratio (CSOR) and recovery factor (RF) for the SAGD process. The outputs of the developed connectionist modeling (i.e., ANN-PSO) were compared with actual data, showing an average error lower than 7%, mostly because of the supremacy of the ANN-PSO method compared to the conventional ANN method and the correlations developed in this study. Furthermore, it is concluded that, among the contributing parameters, reservoir thickness and oil saturation have the most significant impacts on RF and CSOR during SAGD operations. The current study confirms the potential of hybrid connectionist modeling to screen heavy-oil fractured reservoirs for the SAGD process.