Simultaneus prediction of four kinematic variables for a brain-machine interface using a single recurrent neural network

Low-cost open hardware system for behavioural experiments simultaneously with electrophysiological recordings

A major frontier in neuroscience is to find neural correlates of perception, learning, decision making, and a variety of other types of behavior. In the last decades, modern devices allow simultaneous recordings of different operant responses and the electrical activity of large neuronal populations. However, the commercially available instruments for studying operant conditioning are expensive, and the design of low-cost chambers has emerged as an appealing alternative to resource-limited laboratories engaged in animal behavior. In this article, we provide a full description of a platform that records the operant behavior and synchronizes it with the electrophysiological activity. The programming of this platform is open source, flexible, and adaptable to a wide range of operant conditioning tasks. We also show results of operant conditioning experiments with freely moving rats with simultaneous electrophysiological recordings.

Inhibition of Long-Term Variability in Decoding Forelimb Trajectory Using Evolutionary Neural Networks With Error-Correction Learning

Objective: In brain machine interfaces (BMIs), the functional mapping between neural activities and kinematic parameters varied over time owing to changes in neural recording conditions. The variability in neural recording conditions might result in unstable long-term decoding performance. Relevant studies trained decoders with several days of training data to make them inherently robust to changes in neural recording conditions. However, these decoders might not be robust to changes in neural recording conditions when only a few days of training data are available. In time-series prediction and feedback control system, an error feedback was commonly adopted to reduce the effects of model uncertainty. This motivated us to introduce an error feedback to a neural decoder for dealing with the variability in neural recording conditions. Approach: We proposed an evolutionary constructive and pruning neural network with error feedback (ECPNN-EF) as a neural decoder. The ECPNN-EF with partially connected topology decoded the instantaneous firing rates of each sorted unit into forelimb movement of a rat. Furthermore, an error feedback was adopted as an additional input to provide kinematic information and thus compensate for changes in functional mapping. The proposed neural decoder was trained on data collected from a water reward-related lever-pressing task for a rat. The first 2 days of data were used to train the decoder, and the subsequent 10 days of data were used to test the decoder. Main Results: The ECPNN-EF under different settings was evaluated to better understand the impact of the error feedback and partially connected topology. The experimental results demonstrated that the ECPNN-EF achieved significantly higher daily decoding performance with smaller daily variability when using the error feedback and partially connected topology. Significance: These results suggested that the ECPNN-EF with partially connected topology could cope with both within- and across-day changes in neural recording conditions. The error feedback in the ECPNN-EF compensated for decreases in decoding performance when neural recording conditions changed. This mechanism made the ECPNN-EF robust against changes in functional mappings and thus improved the long-term decoding stability when only a few days of training data were available.

Comparisons between linear and nonlinear methods for decoding motor cortical activities of monkey

Brain Machine Interfaces (BMI) aim at building a direct communication link between the neural system and external devices. The decoding of neuronal signals is one of the important steps in BMI systems. Existing decoding methods commonly fall into two categories, i.e., linear methods and nonlinear methods. This paper compares the performance between the two kinds of methods in the decoding of motor cortical activities of a monkey. Kalman filter (KF) is chosen as an example of linear methods, and General Regression Neural Network (GRNN) and Support Vector Regression (SVR) are two nonlinear approaches evaluated in our work. The experiments are conducted to reconstruct 2D trajectories in a center-out task. The correlation coefficient (CC) and the root mean square error (RMSE) are used to assess the performance. The experimental results show that GRNN and SVR achieve better performance than Kalman filter with average improvements of about 30% in CC and 40% in RMSE. This demonstrates that nonlinear models can better encode the relationship between the neuronal signals and response. In addition, GRNN and SVR are more effective than Kalman filter on noisy data.

Unscented Kalman filter for brain-machine interfaces

Brain machine interfaces (BMIs) are devices that convert neural signals into commands to directly control artificial actuators, such as limb prostheses. Previous real-time methods applied to decoding behavioral commands from the activity of populations of neurons have generally relied upon linear models of neural tuning and were limited in the way they used the abundant statistical information contained in the movement profiles of motor tasks. Here, we propose an n-th order unscented Kalman filter which implements two key features: (1) use of a non-linear (quadratic) model of neural tuning which describes neural activity significantly better than commonly-used linear tuning models, and (2) augmentation of the movement state variables with a history of n-1 recent states, which improves prediction of the desired command even before incorporating neural activity information and allows the tuning model to capture relationships between neural activity and movement at multiple time offsets simultaneously. This new filter was tested in BMI experiments in which rhesus monkeys used their cortical activity, recorded through chronically implanted multielectrode arrays, to directly control computer cursors. The 10th order unscented Kalman filter outperformed the standard Kalman filter and the Wiener filter in both off-line reconstruction of movement trajectories and real-time, closed-loop BMI operation.

The development of brain-machine interface neuroprosthetic devices

The development of brain-machine interface technology is a logical next step in the overall direction of neuroprosthetics. Many of the required technological advances that will be required for clinical translation of brain-machine interfaces are already under development, including a new generation of recording electrodes, the decoding and interpretation of signals underlying intention and planning, actuators for implementation of mental plans in virtual or real contexts, direct somatosensory feedback to the nervous system to refine actions, and training to encourage plasticity in neural circuits. Although pre-clinical studies in nonhuman primates demonstrate high efficacy in a realistic motor task with motor cortical recordings, there are many challenges in the clinical translation of even simple tasks and devices. Foremost among these challenges is the development of biocompatible electrodes capable of long-term, stable recording of brain activity and implantable amplifiers and signal processors that are sufficiently resistant to noise and artifact to faithfully transmit recorded signals to the external environment. Whether there is a suitable market for such new technology depends on its efficacy in restoring and enhancing neural function, its risks of implantation, and its long-term efficacy and usefulness. Now is a critical time in brain-machine interface development because most ongoing studies are science-based and noncommercial, allowing new approaches to be included in commercial schemes under development.