Stabilization of a brain-computer interface via the alignment of low-dimensional spaces of neural activity.

Stabilization of a brain-computer interface via the alignment of low-dimensional spaces of neural activity.
复制标题

DOI:
10.1038/s41551-020-0542-9
复制
发表时间:
2020-07
影响因子:
28.1
通讯作者:
Yu BM
Yu BM
中科院分区:
工程技术1区
文献类型:
--
作者:
Degenhart AD;Bishop WE;Oby ER;Tyler-Kabara EC;Chase SM;Batista AP;Yu BM

文献摘要

参考文献

被引文献

相似文献

神经记录的不稳定性会导致临床脑机接口(bci)不可控。在这里,我们展示了低维神经流形(描述神经元之间特定关联模式的低维空间)的对齐可以用来稳定神经活动,从而在记录不稳定的情况下保持脑机接口的性能。我们通过皮质内脑机接口评估了非人类灵长类动物在存在严重和突然记录不稳定性的情况下,通过在线光标控制的稳定剂。稳定的脑机接口在不同的不稳定条件下和在多个天内恢复了熟练的控制。稳定器不需要了解用户意图,并且可以优于监督重新校准。它稳定了脑机接口,即使神经活动包含很少关于光标移动方向的信息。该稳定剂可能适用于其他神经接口,并可能提高脑机接口的临床生存能力。
The instability of neural recordings can render clinical brain-computer interfaces (BCIs) uncontrollable. Here, we show that the alignment of low-dimensional neural manifolds (low-dimensional spaces that describe specific correlation patterns between neurons) can be used to stabilize neural activity, thereby maintaining BCI performance in the presence of recording instabilities. We evaluated the stabilizer with non-human primates during online cursor control via intracortical BCIs in the presence of severe and abrupt recording instabilities. The stabilized BCIs recovered proficient control under different instability conditions and across multiple days. The stabilizer does not require knowledge of user intent and can outperform supervised recalibration. It stabilized BCIs even when neural activity contained little information about the direction of cursor movement. The stabilizer may be applicable to other neural interfaces and may improve the clinical viability of BCIs.
偏差,最佳线性估计以及基于峰值的大脑计算机界面算法的开环模拟与闭环性能之间的差异。
DOI: 10.1016/j.neunet.2009.05.005
发表时间: 2009-11
期刊: Neural networks : the official journal of the International Neural Network Society
影响因子: --
作者:
Chase SM;Schwartz AB;Kass RE
通讯作者: Kass RE
DOI: 10.1038/s41551-017-0169-7
发表时间: 2017-12
影响因子: 28.1
作者:
Dyer EL;Gheshlaghi Azar M;Perich MG;Fernandes HL;Naufel S;Miller LE;Körding KP
通讯作者: Körding KP
DOI: 10.1088/1741-2552/aa9bfb
发表时间: 2018-04-01
影响因子: 4
作者:
Degenhart, Alan D.;Hiremath, Shivayogi V.;Wang, Wei
通讯作者: Wang, Wei
DOI: 10.1523/jneurosci.2339-15.2016
发表时间: 2016-03-23
影响因子: 5.3
作者:
Flint, Robert D.;Scheid, Michael R.;Slutzky, Marc W.
通讯作者: Slutzky, Marc W.
DOI: 10.1088/1741-2560/13/4/046019
发表时间: 2016-08
影响因子: 4
作者:
Degenhart AD;Eles J;Dum R;Mischel JL;Smalianchuk I;Endler B;Ashmore RC;Tyler-Kabara EC;Hatsopoulos NG;Wang W;Batista AP;Cui XT
通讯作者: Cui XT