Rapid control and feedback rates enhance neuroprosthetic control.

Brain-machine interfaces (BMI) create novel sensorimotor pathways for action. Much as the sensorimotor apparatus shapes natural motor control, the BMI pathway characteristics may also influence neuroprosthetic control. Here, we explore the influence of control and feedback rates, where control rate indicates how often motor commands are sent from the brain to the prosthetic, and feedback rate indicates how often visual feedback of the prosthetic is provided to the subject. We developed a new BMI that allows arbitrarily fast control and feedback rates, and used it to dissociate the effects of each rate in two monkeys. Increasing the control rate significantly improved control even when feedback rate was unchanged. Increasing the feedback rate further facilitated control. We also show that our high-rate BMI significantly outperformed state-of-the-art methods due to higher control and feedback rates, combined with a different point process mathematical encoding model. Our BMI paradigm can dissect the contribution of different elements in the sensorimotor pathway, providing a unique tool for studying neuroprosthetic control mechanisms.

Continuous closed-loop decoder adaptation with a recursive maximum likelihood algorithm allows for rapid performance acquisition in brain-machine interfaces.

Closed-loop decoder adaptation (CLDA) is an emerging paradigm for both improving and maintaining online performance in brain-machine interfaces (BMIs). The time required for initial decoder training and any subsequent decoder recalibrations could be potentially reduced by performing continuous adaptation, in which decoder parameters are updated at every time step during these procedures, rather than waiting to update the decoder at periodic intervals in a more batch-based process. Here, we present recursive maximum likelihood (RML), a CLDA algorithm that performs continuous adaptation of a Kalman filter decoder's parameters. We demonstrate that RML possesses a variety of useful properties and practical algorithmic advantages. First, we show how RML leverages the accuracy of updates based on a batch of data while still adapting parameters on every time step. Second, we illustrate how the RML algorithm is parameterized by a single, intuitive half-life parameter that can be used to adjust the rate of adaptation in real time. Third, we show how even when the number of neural features is very large, RML's memory-efficient recursive update rules can be reformulated to also be computationally fast so that continuous adaptation is still feasible. To test the algorithm in closed-loop experiments, we trained three macaque monkeys to perform a center-out reaching task by using either spiking activity or local field potentials to control a 2D computer cursor. RML achieved higher levels of performance more rapidly in comparison to a previous CLDA algorithm that adapts parameters on a more intermediate timescale. Overall, our results indicate that RML is an effective CLDA algorithm for achieving rapid performance acquisition using continuous adaptation.

Subject-specific modulation of local field potential spectral power during brain-machine interface control in primates.

OBJECTIVE: Intracortical brain-machine interfaces (BMIs) have predominantly utilized spike activity as the control signal. However, an increasing number of studies have shown the utility of local field potentials (LFPs) for decoding motor related signals. Currently, it is unclear how well different LFP frequencies can serve as features for continuous, closed-loop BMI control. APPROACH: We demonstrate 2D continuous LFP-based BMI control using closed-loop decoder adaptation, which adapts decoder parameters to subject-specific LFP feature modulations during BMI control. We trained two macaque monkeys to control a 2D cursor in a center-out task by modulating LFP power in the 0-150 Hz range. MAIN RESULTS: While both monkeys attained control, they used different strategies involving different frequency bands. One monkey primarily utilized the low-frequency spectrum (0-80 Hz), which was highly correlated between channels, and obtained proficient performance even with a single channel. In contrast, the other monkey relied more on higher frequencies (80-150 Hz), which were less correlated between channels, and had greater difficulty with control as the number of channels decreased. We then restricted the monkeys to use only various sub-ranges (0-40, 40-80, and 80-150 Hz) of the 0-150 Hz band. Interestingly, although both monkeys performed better with some sub-ranges than others, they were able to achieve BMI control with all sub-ranges after decoder adaptation, demonstrating broad flexibility in the frequencies that could potentially be used for LFP-based BMI control. SIGNIFICANCE: Overall, our results demonstrate proficient, continuous BMI control using LFPs and provide insight into the subject-specific spectral patterns of LFP activity modulated during control.

Brain-machine interface control using broadband spectral power from local field potentials.

Recent progress in brain-machine interfaces (BMIs) has shown tremendous improvements in task complexity and degree of control. In particular, closed-loop decoder adaptation (CLDA) has emerged as an effective paradigm for both improving and maintaining the performance of BMI systems. Here, we demonstrate the first reported use of a CLDA algorithm to rapidly achieve high-performance control of a BMI based on local field potentials (LFPs). We trained a non-human primate to control a 2-D computer cursor by modulating LFP activity to perform a center-out reaching task, while applying CLDA to adaptively update the decoder. We show that the subject is quickly able to readily reach and hold at all 8 targets with an average success rate of 74% ± 7% (sustained peak rate of 85%), with rapid convergence in the decoder parameters. Moreover, the subject is able to maintain high performance across 4 days with minimal adaptations to the decoder. Our results indicate that CLDA can be used to facilitate LFP-based BMI systems, allowing for both rapid improvement and maintenance of performance.

Likelihood Gradient Ascent (LGA): a closed-loop decoder adaptation algorithm for brain-machine interfaces.

Closed-loop decoder adaptation (CLDA) is an emerging paradigm for improving or maintaining the online performance of brain-machine interfaces (BMIs). Here, we present Likelihood Gradient Ascent (LGA), a novel CLDA algorithm for a Kalman filter (KF) decoder that uses stochastic, gradient-based corrections to update KF parameters during closed-loop BMI operation. LGA's gradient-based paradigm presents a variety of potential advantages over other "batch" CLDA methods, including the ability to update decoder parameters on any time-scale, even on every decoder iteration. Using a closed-loop BMI simulator, we compare the LGA algorithm to the Adaptive Kalman Filter (AKF), a partially gradient-based CLDA algorithm that has been previously tested in non-human primate experiments. In contrast to the AKF's separate mean-squared error objective functions, LGA's update rules are derived directly from a single log likelihood objective, making it one step towards a potentially optimal continuously adaptive CLDA algorithm for BMIs.

Design and analysis of closed-loop decoder adaptation algorithms for brain-machine interfaces.

Closed-loop decoder adaptation (CLDA) is an emerging paradigm for achieving rapid performance improvements in online brain-machine interface (BMI) operation. Designing an effective CLDA algorithm requires making multiple important decisions, including choosing the timescale of adaptation, selecting which decoder parameters to adapt, crafting the corresponding update rules, and designing CLDA parameters. These design choices, combined with the specific settings of CLDA parameters, will directly affect the algorithm's ability to make decoder parameters converge to values that optimize performance. In this article, we present a general framework for the design and analysis of CLDA algorithms and support our results with experimental data of two monkeys performing a BMI task. First, we analyze and compare existing CLDA algorithms to highlight the importance of four critical design elements: the adaptation timescale, selective parameter adaptation, smooth decoder updates, and intuitive CLDA parameters. Second, we introduce mathematical convergence analysis using measures such as mean-squared error and KL divergence as a useful paradigm for evaluating the convergence properties of a prototype CLDA algorithm before experimental testing. By applying these measures to an existing CLDA algorithm, we demonstrate that our convergence analysis is an effective analytical tool that can ultimately inform and improve the design of CLDA algorithms.

Closed-loop decoder adaptation on intermediate time-scales facilitates rapid BMI performance improvements independent of decoder initialization conditions.

Closed-loop decoder adaptation (CLDA) shows great promise to improve closed-loop brain-machine interface (BMI) performance. Developing adaptation algorithms capable of rapidly improving performance, independent of initial performance, may be crucial for clinical applications where patients have limited movement and sensory abilities due to motor deficits. Given the subject-decoder interactions inherent in closed-loop BMIs, the decoder adaptation time-scale may be of particular importance when initial performance is limited. Here, we present SmoothBatch, a CLDA algorithm which updates decoder parameters on a 1-2 min time-scale using an exponentially weighted sliding average. The algorithm was experimentally tested with one nonhuman primate performing a center-out reaching BMI task. SmoothBatch was seeded four ways with varying offline decoding power: 1) visual observation of a cursor ( n = 20), 2) ipsilateral arm movements ( n = 8), 3) baseline neural activity ( n = 17), and 4) arbitrary weights ( n = 11). SmoothBatch rapidly improved performance regardless of seeding, with performance improvements from 0.018 ±0.133 successes/min to > 8 successes/min within 13.1 ±5.5 min ( n = 56). After decoder adaptation ceased, the subject maintained high performance. Moreover, performance improvements were paralleled by SmoothBatch convergence, suggesting that CLDA involves a co-adaptation process between the subject and the decoder.

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.