Tailoring deep learning for real-time brain-computer interfaces: From offline models to calibration-free online decoding
This work addresses the problem of limited deep learning adoption in real-time BCIs for users needing immediate feedback, though it appears incremental by modifying existing offline models.
The paper tackled the challenge of adapting deep learning for real-time brain-computer interfaces by introducing realtime adaptive pooling (RAP), which enables calibration-free online decoding, reduces computational complexity, and leverages domain adaptation to address data scarcity, resulting in a robust framework that preserves privacy and supports co-adaptive systems.
Despite the growing success of deep learning (DL) in offline brain-computer interfaces (BCIs), its adoption in real-time applications remains limited due to three primary challenges. First, most DL solutions are designed for offline decoding, making the transition to online decoding unclear. Second, the use of sliding windows in online decoding substantially increases computational complexity. Third, DL models typically require large amounts of training data, which are often scarce in BCI applications. To address these challenges and enable real-time, cross-subject decoding without subject-specific calibration, we introduce realtime adaptive pooling (RAP), a novel parameter-free method. RAP seamlessly modifies the pooling layers of existing offline DL models to meet online decoding requirements. It also reduces computational complexity during training by jointly decoding consecutive sliding windows. To further alleviate data requirements, our method leverages source-free domain adaptation, enabling privacy-preserving adaptation across varying amounts of target data. Our results demonstrate that RAP provides a robust and efficient framework for real-time BCI applications. It preserves privacy, reduces calibration demands, and supports co-adaptive BCI systems, paving the way for broader adoption of DL in online BCIs. These findings lay a strong foundation for developing user-centered, high-performance BCIs that facilitate immediate feedback and user learning.