Active Inference for Adaptive BCI: application to the P300 Speller
This provides a flexible framework for adaptive BCIs, potentially improving communication for users with disabilities, though it is incremental as it builds on existing Bayesian methods.
The paper tackled the lack of a general framework for adaptive Brain-Computer Interfaces (BCIs) by applying Active Inference, a Bayesian approach, to infer user intentions and optimize performance. In P300-speller simulations, it outperformed traditional algorithms with bit rate increases of 18% to 59%.
Adaptive Brain-Computer interfaces (BCIs) have shown to improve performance, however a general and flexible framework to implement adaptive features is still lacking. We appeal to a generic Bayesian approach, called Active Inference (AI), to infer user's intentions or states and act in a way that optimizes performance. In realistic P300-speller simulations, AI outperforms traditional algorithms with an increase in bit rate between 18% and 59%, while offering a possibility of unifying various adaptive implementations within one generic framework.