Multi-Task Learning for Commercial Brain Computer Interfaces

Abstract

In the field of Brain Computer Interfaces, one of the most crucial hindrances towards everyday applicability is the problem of subject-to-subject generalization. This adheres to the fact that neural signals vary significantly across subjects, because of the inherent person specific variability, rendering a subject calibration process necessary for the pattern recognition mechanisms of a BCI to achieve a notable performance. In the present work, we explore this phenomenon on two open datasets from mental monitoring experiments which utilized a commercial BCI device (Neurosky). This passive BCI setting with economical hardware is one of the must promising in terms of commercial appeal and hence it has more potential to be employed by multiple subjects-users. We visualize the so-called inter subject variability problem and apply machine learning methods commonly used in BCI literature. Subsequently we employ multi-task learning algorithms, setting each subject specific classification as a separate task. The experiments reveal that multi-task approaches achieve better accuracy with increasing number of subjects in contrast to conventional models, while providing insights that are consistent among subjects and agree with the relevant literature.