Meeting brain–computer interface user performance expectations using a deep neural network decoding framework

Brain–computer interface (BCI) neurotechnology has the potential to reduce disability associated with paralysis by translating neural activity into control of assistive devices^{1,2,3,4,5,6,7,8,9}. Surveys of potential end-users have identified key BCI system features^{10,11,12,13,14}, including high accuracy, minimal daily setup, rapid response times, and multifunctionality. These performance characteristics are primarily influenced by the BCI’s neural decoding algorithm^1,15, which is trained to associate neural activation patterns with intended user actions. Here, we introduce a new deep neural network¹⁶ decoding framework for BCI systems enabling discrete movements that addresses these four key performance characteristics. Using intracortical data from a participant with tetraplegia, we provide offline results demonstrating that our decoder is highly accurate, sustains this performance beyond a year without explicit daily retraining by combining it with an unsupervised updating procedure^{3,17,18,19,20}, responds faster than competing methods⁸, and can increase functionality with minimal retraining by using a technique known as transfer learning²¹. We then show that our participant can use the decoder in real-time to reanimate his paralyzed forearm with functional electrical stimulation (FES), enabling accurate manipulation of three objects from the grasp and release test (GRT)²². These results demonstrate that deep neural network decoders can advance the clinical translation of BCI technology.