Mixed-norm Regularization for Brain Decoding
This addresses data scarcity in brain-computer interfaces for subjects with poor performance, but it is incremental as it builds on existing regularization methods.
The paper tackles sensor selection in brain-computer interfaces by using mixed-norm regularization, showing improved performance on three datasets, with multi-task learning yielding significant gains for subjects with limited data.
This work investigates the use of mixed-norm regularization for sensor selection in Event-Related Potential (ERP) based Brain-Computer Interfaces (BCI). The classification problem is cast as a discriminative optimization framework where sensor selection is induced through the use of mixed-norms. This framework is extended to the multi-task learning situation where several similar classification tasks related to different subjects are learned simultaneously. In this case, multi-task learning helps in leveraging data scarcity issue yielding to more robust classifiers. For this purpose, we have introduced a regularizer that induces both sensor selection and classifier similarities. The different regularization approaches are compared on three ERP datasets showing the interest of mixed-norm regularization in terms of sensor selection. The multi-task approaches are evaluated when a small number of learning examples are available yielding to significant performance improvements especially for subjects performing poorly.