Brain-Computer Interfaces (BCI) provide effective tools aimed at recognizing different brain activities, translate them into actions, and enable humans to directly communicate through them. In this context, the need for strong recognition performances results in increasingly sophisticated machine learning (ML) techniques, which may result in poor performance in a real application (e.g., limiting a real-time implementation). Here, we propose an ensemble approach to effectively balance between ML performance and computational costs in a BCI framework. The proposed model builds a classifier by combining different ML models (base-models) that are specialized to different classification sub-problems. More specifically, we employ this strategy with an ensemble-based architecture consisting of multi-layer perceptrons, and test its performance on a publicly available electroencephalography-based BCI dataset with four-class motor imagery tasks. Compared to previously proposed models tested on the same dataset, the proposed approach provides greater average classification performances and lower inter-subject variability.