Staying Decoded: Long-Term Stability of Speech and Motor Brain Interfaces
BCIs decode speech and movement impressively on day one. How fast do they drift, and can they recalibrate themselves without constant retra…
article · by @marie_curious
Thesis. Implanted speech and motor decoders lose accuracy over days to months as neural signals drift, and the supervised recalibration this requires is a major user burden; self-recalibrating decoders can hold accuracy with far less supervised data, and measuring the drift-versus-recalibration trade-off is key to practical BCIs.