Suppr超能文献

用于脑机接口的脉冲神经网络解码器

Spiking Neural Network Decoder for Brain-Machine Interfaces.

作者信息

Dethier Julie, Gilja Vikash, Nuyujukian Paul, Elassaad Shauki A, Shenoy Krishna V, Boahen Kwabena

机构信息

Department of Bioengineering, Stanford University, Stanford, CA 94305, USA.

Department of Computer Science and Stanford Institute for Neuro-Innovation and Translational Neuroscience, Stanford University, Stanford, CA 94305, USA.

出版信息

Int IEEE EMBS Conf Neural Eng. 2011. doi: 10.1109/NER.2011.5910570.

Abstract

We used a spiking neural network (SNN) to decode neural data recorded from a 96-electrode array in premotor/motor cortex while a rhesus monkey performed a point-to-point reaching arm movement task. We mapped a Kalman-filter neural prosthetic decode algorithm developed to predict the arm's velocity on to the SNN using the Neural Engineering Framework and simulated it using , a freely available software package. A 20,000-neuron network matched the standard decoder's prediction to within 0.03% (normalized by maximum arm velocity). A 1,600-neuron version of this network was within 0.27%, and run in real-time on a 3GHz PC. These results demonstrate that a SNN can implement a statistical signal processing algorithm widely used as the decoder in high-performance neural prostheses (Kalman filter), and achieve similar results with just a few thousand neurons. Hardware SNN implementations-neuromorphic chips-may offer power savings, essential for realizing fully-implantable cortically controlled prostheses.

摘要

我们使用了一个脉冲神经网络(SNN)来解码从恒河猴运动前区/运动皮层的96电极阵列记录的神经数据,此时恒河猴正在执行点对点的手臂伸展运动任务。我们使用神经工程框架将一种为预测手臂速度而开发的卡尔曼滤波器神经假体解码算法映射到SNN上,并使用一个免费的软件包对其进行模拟。一个20,000个神经元的网络将标准解码器的预测匹配到了0.03%以内(以最大手臂速度进行归一化)。这个网络的一个1,600个神经元版本的误差在0.27%以内,并且可以在一台3GHz的个人电脑上实时运行。这些结果表明,一个SNN可以实现一种广泛用作高性能神经假体解码器的统计信号处理算法(卡尔曼滤波器),并且仅用几千个神经元就能取得类似的结果。硬件SNN实现——神经形态芯片——可能会节省功耗,这对于实现完全可植入的皮层控制假体至关重要。

相似文献

1
Spiking Neural Network Decoder for Brain-Machine Interfaces.
Int IEEE EMBS Conf Neural Eng. 2011. doi: 10.1109/NER.2011.5910570.
3
Design and validation of a real-time spiking-neural-network decoder for brain-machine interfaces.
J Neural Eng. 2013 Jun;10(3):036008. doi: 10.1088/1741-2560/10/3/036008. Epub 2013 Apr 10.
4
A Bidirectional Brain-Machine Interface Featuring a Neuromorphic Hardware Decoder.
Front Neurosci. 2016 Dec 9;10:563. doi: 10.3389/fnins.2016.00563. eCollection 2016.
6
An Improved Unscented Kalman Filter Based Decoder for Cortical Brain-Machine Interfaces.
Front Neurosci. 2016 Dec 22;10:587. doi: 10.3389/fnins.2016.00587. eCollection 2016.
7
Adaptive decoding for brain-machine interfaces through Bayesian parameter updates.
Neural Comput. 2011 Dec;23(12):3162-204. doi: 10.1162/NECO_a_00207. Epub 2011 Sep 15.
8
sPyNNaker: A Software Package for Running PyNN Simulations on SpiNNaker.
Front Neurosci. 2018 Nov 20;12:816. doi: 10.3389/fnins.2018.00816. eCollection 2018.
9
Adaptive Neural Decoder for Prosthetic Hand Control.
Front Neurosci. 2021 Apr 8;15:590775. doi: 10.3389/fnins.2021.590775. eCollection 2021.

引用本文的文献

2
Cortical Control of Virtual Self-Motion Using Task-Specific Subspaces.
J Neurosci. 2022 Jan 12;42(2):220-239. doi: 10.1523/JNEUROSCI.2687-20.2021. Epub 2021 Oct 29.
3
Brain-controlled muscle stimulation for the restoration of motor function.
Neurobiol Dis. 2015 Nov;83:180-90. doi: 10.1016/j.nbd.2014.10.014. Epub 2014 Oct 28.
5
Hidden Markov model and support vector machine based decoding of finger movements using electrocorticography.
J Neural Eng. 2013 Oct;10(5):056020. doi: 10.1088/1741-2560/10/5/056020. Epub 2013 Sep 18.
6
Design and validation of a real-time spiking-neural-network decoder for brain-machine interfaces.
J Neural Eng. 2013 Jun;10(3):036008. doi: 10.1088/1741-2560/10/3/036008. Epub 2013 Apr 10.
7
A recurrent neural network for closed-loop intracortical brain-machine interface decoders.
J Neural Eng. 2012 Apr;9(2):026027. doi: 10.1088/1741-2560/9/2/026027. Epub 2012 Mar 19.

本文引用的文献

1
Silicon-Neuron Design: A Dynamical Systems Approach.
IEEE Trans Circuits Syst I Regul Pap. 2011;58(5):1034-1043. doi: 10.1109/TCSI.2010.2089556.
2
Challenges and opportunities for next-generation intracortically based neural prostheses.
IEEE Trans Biomed Eng. 2011 Jul;58(7):1891-9. doi: 10.1109/TBME.2011.2107553. Epub 2011 Jan 20.
3
Neural control of computer cursor velocity by decoding motor cortical spiking activity in humans with tetraplegia.
J Neural Eng. 2008 Dec;5(4):455-76. doi: 10.1088/1741-2560/5/4/010. Epub 2008 Nov 18.
4
Thermal impact of an active 3-D microelectrode array implanted in the brain.
IEEE Trans Neural Syst Rehabil Eng. 2007 Dec;15(4):493-501. doi: 10.1109/TNSRE.2007.908429.
5
Neurotech for neuroscience: unifying concepts, organizing principles, and emerging tools.
J Neurosci. 2007 Oct 31;27(44):11807-19. doi: 10.1523/JNEUROSCI.3575-07.2007.
6
Higher-dimensional neurons explain the tuning and dynamics of working memory cells.
J Neurosci. 2006 Apr 5;26(14):3667-78. doi: 10.1523/JNEUROSCI.4864-05.2006.
7
A unified approach to building and controlling spiking attractor networks.
Neural Comput. 2005 Jun;17(6):1276-314. doi: 10.1162/0899766053630332.
8
Neuromorphic Microchips.
Sci Am. 2005 May;292(5):56-63. doi: 10.1038/scientificamerican0505-56.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验