Rethinking BCI Paradigm and Machine Learning Algorithm as a Symbiosis: Zero Calibration, Guaranteed Convergence and High Decoding Performance

In the past, the decoding quality of brain-computer interface (BCI) systems was often enhanced by independently improving either the machine learning algorithms or the BCI paradigms. We propose to take a novel perspective instead by optimizing the whole system, paradigm and decoder, jointly. To exemplify this holistic idea, we introduce learning from label proportions (LLP) as a new classification approach and prove its value for visual event-related potential (ERP) signals of the EEG. LLP utilizes the existence of subgroups with different label proportions in the data. This leads to a conceptually simple BCI system which combines previously unseen capabilities: (1) it does not require calibration and learns from unlabeled data, (2) under i.i.d. conditions, LLP is guaranteed to obtain the optimal decoder for online data, (3) under violation of stationarity assumptions, LLP can continuously adapt to the changing data, and (4) it can, in practice, replace a traditional supervised decoder when combined with an expectation-maximization algorithm.