Brain control of bimanual movement enabled by recurrent neural networks.

Brain control of bimanual movement enabled by recurrent neural networks.
复制标题

循环神经网络实现的双手运动的大脑控制

DOI:
10.1038/s41598-024-51617-3
复制
发表时间:
2024-01-18
期刊:
影响因子:
4.6
通讯作者:
--
中科院分区:
综合性期刊3区
文献类型:
--
作者:

文献摘要

参考文献

相似文献

脑机接口到目前为止主要集中在实现对单个效应器的控制上,例如单个计算机光标或机械臂。恢复多效应器运动可能为瘫痪患者解锁更多功能(例如,双手运动)。然而,解码多个效应器的同时运动可能具有挑战性,因为我们最近发现一种组合神经编码将所有肢体的运动联系起来,并且在双效应器运动过程中神经调谐呈非线性变化。在这里,我们通过神经网络(NN)解码器展示了对两个光标进行高质量双手控制的可行性。通过模拟,我们表明,随着对双手的神经调谐相关性越来越强,神经网络利用神经的“偏侧性”维度来区分左手和右手的运动。在训练用于双光标控制的循环神经网络(RNNs)时,我们开发了一种方法,通过在时间上拉伸/压缩训练数据并对其重新排序来改变训练数据的时间结构,我们表明这有助于RNNs成功地推广到在线环境。通过这种方法,我们证明了一名瘫痪患者可以同时控制两个计算机光标。我们的研究结果表明,如果神经网络解码器被设计为能够转移到在线环境,那么它对于多效应器解码可能是有利的。
Brain-computer interfaces have so far focused largely on enabling the control of a single effector, for example a single computer cursor or robotic arm. Restoring multi-effector motion could unlock greater functionality for people with paralysis (e.g., bimanual movement). However, it may prove challenging to decode the simultaneous motion of multiple effectors, as we recently found that a compositional neural code links movements across all limbs and that neural tuning changes nonlinearly during dual-effector motion. Here, we demonstrate the feasibility of high-quality bimanual control of two cursors via neural network (NN) decoders. Through simulations, we show that NNs leverage a neural ‘laterality’ dimension to distinguish between left and right-hand movements as neural tuning to both hands become increasingly correlated. In training recurrent neural networks (RNNs) for two-cursor control, we developed a method that alters the temporal structure of the training data by dilating/compressing it in time and re-ordering it, which we show helps RNNs successfully generalize to the online setting. With this method, we demonstrate that a person with paralysis can control two computer cursors simultaneously. Our results suggest that neural network decoders may be advantageous for multi-effector decoding, provided they are designed to transfer to the online setting.
MBD2 缺失通过调节细胞内锌稳态改善 LPS 诱导的小鼠肺泡上皮细胞凋亡和 ALI
DOI: 10.1096/fj.202100924rr
发表时间: 2022-02-01
期刊: FASEB JOURNAL
影响因子: 4.8
作者:
Liu, Jiqiang;Yao, Shuo;Xiao, Bing
通讯作者: Xiao, Bing
草酰乙酸通过减轻氧化应激和线粒体功能障碍改善百草枯诱导的急性肺损伤
DOI: 10.3389/fphar.2022.1029775
发表时间: 2022
影响因子: 5.6
作者:
通讯作者: --
褪黑素预防急性肺损伤的新机制:通过 SIRT3 依赖性 SOD2 脱乙酰作用保留肺上皮细胞的线粒体质量控制
DOI: 10.1007/s00018-022-04628-0
发表时间: 2022-12-01
影响因子: 8
作者:
Li, Ning;Xiong, Rui;Geng, Qing
通讯作者: Geng, Qing
MitoQ通过调节Nrf2/Drp1通路减轻LPS介导的急性肺损伤
DOI: 10.1016/j.freeradbiomed.2021.01.045
发表时间: 2021-02-05
影响因子: 7.4
作者:
Hou, Lei;Zhang, Jinyuan;Wang, Xiangrui
通讯作者: Wang, Xiangrui
DOI: 10.1038/nature14362
发表时间: 2015-04-09
期刊: NATURE
影响因子: 64.8
作者:
Schoors, Sandra;Bruning, Ulrike;Missiaen, Rindert;Queiroz, Karla C. S.;Borgers, Gitte;Elia, Ilaria;Zecchin, Annalisa;Cantelmo, Anna Rita;Christen, Stefan;Goveia, Jermaine;Heggermont, Ward;Godde, Lucica;Vinckier, Stefan;Van Veldhoven, Paul P.;Eelen, Guy;Schoonjans, Luc;Gerhardt, Holger;Dewerchin, Mieke;Baes, Myriam;De Bock, Katrien;Ghesquiere, Bart;Lunt, Sophia Y.;Fendt, Sarah-Maria;Carmeliet, Peter
通讯作者: Carmeliet, Peter