Neural interface systems with on-device computing: machine learning and neuromorphic architectures.
Neural interface systems with on-device computing: machine learning and neuromorphic architectures.
复制标题
DOI：
10.1016/j.copbio.2021.10.012
复制
发表时间：
2021-11
影响因子：
7.7
通讯作者：
Jerald Yoo;Mahsa Shoaran
中科院分区：
文献类型：
--
作者：
Jerald Yoo;Mahsa Shoaran
重点神经接口在通道数量和形状因子方面不断改进。低功耗机器学习和神经形态处理器可以集成到神经设备上。具有设备上计算的神经系统芯片可以实现实时闭环治疗。片上机器学习消除了向外部设备传输高功耗数据的过程。神经接口和脑机接口（BMI）的开发系统能够治疗神经系统疾病，包括认知、感觉和运动功能障碍。虽然神经接口的形状因素稳步下降，但最近的发展目标是普及植入式。沿着电极、神经记录和神经刺激电路的进步，疾病生物标志物和机器学习算法的集成实现了对神经活动的实时和现场处理，而不需要高功耗的遥测。最近将人工智能和机器学习与现代神经接口相结合的趋势将导致新一代低功耗，智能和小型化的治疗设备，用于各种神经和精神疾病。本文综述了“片上”机器学习和神经形态结构的最新发展，这是设计下一代临床可行的神经接口系统的关键难题之一。
HighlightsNeural interfaces continue to improve in channel count and form factor.Low-power machine learning and neuromorphic processors can be integrated onto neural devices.Neural system-on-chips with on-device computing enable real-time closed-loop therapies.On-chip machine learning eliminates power-hungry data movement to external devices.Development of neural interface and brain-machine interface (BMI) systems enables the treatment of neurological disorders including cognitive, sensory, and motor dysfunctions. While neural interfaces have steadily decreased in form factor, recent developments target pervasive implantables. Along with advances in electrodes, neural recording, and neurostimulation circuits, integration of disease biomarkers and machine learning algorithms enables real-time and on-site processing of neural activity with no need for power-demanding telemetry. This recent trend on combining artificial intelligence and machine learning with modern neural interfaces will lead to a new generation of low-power, smart, and miniaturized therapeutic devices for a wide range of neurological and psychiatric disorders. This paper reviews the recent development of the ‘on-chip’machine learning and neuromorphic architectures, which is one of the key puzzles in devising next-generation clinically viable neural interface systems.