Design and validation of a real-time spiking-neural-network decoder for brain-machine interfaces.
Design and validation of a real-time spiking-neural-network decoder for brain-machine interfaces.
复制标题
DOI：
10.1088/1741-2560/10/3/036008
复制
发表时间：
2013-06
影响因子：
4
通讯作者：
Boahen K
中科院分区：
文献类型：
--
作者：
Dethier J;Nuyujukian P;Ryu SI;Shenoy KV;Boahen K
皮质控制运动假体旨在恢复因神经疾病和损伤而丧失的功能。几个概念验证演示显示了令人鼓舞的结果，但临床转化的障碍仍然存在。特别是，皮质内假体必须满足严格的功耗限制，以免损伤皮质。一种可能的解决方案是使用超低功耗的神经形态芯片来解码这些皮质内植入物的神经信号。第一步是在模拟中探索将脑机接口（BMI）应用的解码算法转换为尖峰神经网络（snn）的可行性。在这里，我们通过使用神经工程框架（NEF）在模拟SNN中实现现有的基于卡尔曼滤波器的解码器来证明该方法的有效性，NEF是一种将控制算法映射到SNN的通用方法。为了测量该系统的鲁棒性和泛化性，我们在两只恒河猴的闭环BMI实验中进行了在线测试。在这两只猴子中，使用2000个神经元SNN实现的卡尔曼滤波器与使用标准浮点技术实现的卡尔曼滤波器具有相当的性能。这些结果证明了SNN统计信号处理算法在不同猴子和不同任务上的可跟踪性，表明在神经形态芯片上实现的SNN解码器可能是低功耗全植入假体的可行计算平台。该闭环解码器系统的验证及其鲁棒性和泛化的证明为使用NEF在超低功耗神经形态芯片上实现SNN提供了希望。
Cortically-controlled motor prostheses aim to restore functions lost to neurological disease and injury. Several proof of concept demonstrations have shown encouraging results, but barriers to clinical translation still remain. In particular, intracortical prostheses must satisfy stringent power dissipation constraints so as not to damage cortex. One possible solution is to use ultra-low power neuromorphic chips to decode neural signals for these intracortical implants. The first step is to explore in simulation the feasibility of translating decoding algorithms for brain-machine interface (BMI) applications into spiking neural networks (SNNs). Here we demonstrate the validity of the approach by implementing an existing Kalman-filter-based decoder in a simulated SNN using the Neural Engineering Framework (NEF), a general method for mapping control algorithms onto SNNs. To measure this system’s robustness and generalization, we tested it online in closed-loop BMI experiments with two rhesus monkeys. Across both monkeys, a Kalman filter implemented using a 2000-neuron SNN has comparable performance to that of a Kalman filter implemented using standard floating point techniques. These results demonstrate the tractability of SNN implementations of statistical signal processing algorithms on different monkeys and for several tasks, suggesting that a SNN decoder, implemented on a neuromorphic chip, may be a feasible computational platform for low-power fully-implanted prostheses. The validation of this closed-loop decoder system and the demonstration of its robustness and generalization hold promise for SNN implementations on an ultra-low power neuromorphic chip using the NEF.
登录
查看更多内容
影响因子：
64.8
作者：
Ethier, C.;Oby, E. R.;Bauman, M. J.;Miller, L. E.
通讯作者：
Miller, L. E.
DOI：
10.1109/tnsre.2009.2023293
发表时间：
2009-08-01
影响因子：
4.9
作者：
Chestek, Cynthia A.;Gilja, Vikash;Shenoy, Krishna V.
通讯作者：
Shenoy, Krishna V.
DOI：
10.1109/tnsre.2007.908429
发表时间：
2007-12-01
影响因子：
4.9
作者：
Kim, Sohee;Tathireddy, Prashant;Solzbacher, Florian
通讯作者：
Solzbacher, Florian
影响因子：
25
作者：
Ganguly, Karunesh;Dimitrov, Dragan F.;Wallis, Jonathan D.;Carmena, Jose M.
通讯作者：
Carmena, Jose M.
影响因子：
64.8
作者：
Laubach, M;Wessberg, J;Nicolelis, MAL
通讯作者：
Nicolelis, MAL