Exploring time-scales of closed-loop decoder adaptation in brain-machine interfaces

Performing closed-loop modifications of a brain-machine interface (BMI) decoder is a technique that shows great promise for improving performance. We compare two algorithms for implementing adaptations that update decoder parameters on different time-scales (discrete batches vs. online), and present experimental results of a non-human primate performing a standard center-out BMI task. To ensure that our experimental training models are representative of a broad range of paralyzed patients, our decoders were initially trained using neural activity recorded during subject observation of cursor movement. We find that both closed-loop adaptation algorithms can be used to boost BMI performance from 20-30% to 80%, yielding movement kinematics similar to natural arm movements. Based on insights derived from the performance of each algorithm, we propose that a hybrid of batch and online decoder adaptation may be the best approach.