Despite the rapid progress and interest in brain-machine interfaces that restore motor function, the performance of prosthetic fingers and limbs has yet to mimic native function. The algorithm that converts brain signals to a control signal for the prosthetic device is one of the limitations in achieving rapid and realistic finger movements. To achieve more realistic finger movements, we developed a shallow feed-forward neural network to decode real-time two-degree-of-freedom finger movements in two adult male rhesus macaques. Using a two-step training method, a recalibrated feedback intention–trained (ReFIT) neural network is introduced to further improve performance. In 7 days of testing across two animals, neural network decoders, with higher-velocity and more natural appearing finger movements, achieved a 36% increase in throughput over the ReFIT Kalman filter, which represents the current standard. The neural network decoders introduced herein demonstrate real-time decoding of continuous movements at a level superior to the current state-of-the-art and could provide a starting point to using neural networks for the development of more naturalistic brain-controlled prostheses.

Resting-state functional magnetic resonance imaging (rs-fMRI) is an immensely powerful method in neuroscience that uses the blood oxygenation level-dependent (BOLD) signal to record and analyze neural activity in the brain. We examined the complexity of brain activity acquired by rs-fMRI to determine whether it exhibits variation across brain regions. In this study the complexity of regional brain activity was analyzed by calculating the sample entropy of 200 whole-brain BOLD volumes as well as of distinct brain networks, cortical regions, and subcortical regions of these brain volumes. It can be seen that different brain regions and networks exhibit distinctly different levels of entropy/complexity, and that entropy in the brain significantly differs between brains at rest and during task performance.

Despite the rapid progress and interest in brain-machine interfaces that restore motor function, the performance of prosthetic fingers and limbs has yet to mimic native function. The algorithm that converts brain signals to a control signal for the prosthetic device is one of the limitations in achieving rapid and realistic finger movements. To achieve more realistic finger movements, we developed a shallow feed-forward neural network, loosely inspired by the biological neural pathway, to decode real-time two-degree-of-freedom finger movements. Using a two-step training method, a recalibrated feedback intention-trained (ReFIT) neural network achieved a higher throughput with higher finger velocities and more natural appearing finger movements than the ReFIT Kalman filter, which represents the current standard. The neural network decoders introduced herein are the first to demonstrate real-time decoding of continuous movements at a level superior to the current state-of-the-art and could provide a starting point to using neural networks for the development of more naturalistic brain-controlled prostheses.

Brain-machine interfaces (BMIs) can restore motor function to people with paralysis but are currently limited by the accuracy of real-time decoding algorithms. Recurrent neural networks (RNNs) using modern training techniques have shown promise in accurately predicting movements from neural signals but have yet to be rigorously evaluated against other decoding algorithms in a closed-loop setting. Here we compared RNNs to other neural network architectures in real-time, continuous decoding of finger movements using intracortical signals from nonhuman primates. Across one and two finger online tasks, LSTMs (a type of RNN) outperformed convolutional and transformer-based neural networks, averaging 18% higher throughput than the convolution network. On simplified tasks with a reduced movement set, RNN decoders were allowed to memorize movement patterns and matched able-bodied control. Performance gradually dropped as the number of distinct movements increased but did not go below fully continuous decoder performance. Finally, in a two-finger task where one degree-of-freedom had poor input signals, we recovered functional control using RNNs trained to act both like a movement classifier and continuous decoder. Our results suggest that RNNs can enable functional real-time BMI control by learning and generating accurate movement patterns.