Neurophysiologically-informed Design of Flexible, 2-learner Brain-Machine Interfaces for Robust and Skillful Performance

基于神经生理学的灵活 2 学习者脑机接口设计，实现稳健而熟练的表现

• 批准号: 9890015
• 负责人: Jose Miguel Carmena
• 金额: $ 34.34万
• 依托单位: UNIVERSITY OF CALIFORNIA BERKELEY
• 依托单位国家: 美国
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-03-01 至 2023-02-28
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9890015
• 关键词: Affect; Animal Model; Architecture; Automobile Driving; Basic Science; Brain; Chronic; Data Set; Development; Engineering; Feedback; Future; Goals; Implant; Individual; Knowledge; Learning; Learning Skill; Location; Macaca; Machine Learning; Microelectrodes; Modeling; Monkeys; Motor; Motor Cortex; Movement; Outcome; Patients; Pattern; Performance; Population; Privatization; Protocols documentation; Resistance; Science; Series; Structure; System; Testing; Time; Training; Update; Validation; Work; brain machine interface; clinical development; computational basis; denoising; design; experimental study; flexibility; improved; indexing; insight; learning strategy; movement practice; nervous system disorder; neural patterning; neurodevelopment; neurophysiology; neuroprosthesis; next generation; nonhuman primate; relating to nervous system; skills

PROJECT SUMMARY This proposal aims to elucidate the computational and neural basis of neuroprosthetic skill learning by leveraging recent advances in the science and engineering of closed-loop brain-machine interfacing. The outcome of the proposed work has the potential to guide the development of the next generation of neurophysiologically-informed, cortically-controlled neuroprosthetic systems for patients with neurological disorders. State-of-the-art brain-machine interfaces (BMIs) leverage machine learning to rapidly calibrate to the neural activity of individuals, but performance also benefits from subjects learning to reliably produce desired neural activity patterns. The basic science and engineering principles of designing such a “2-learner BMI” in which the brain and machine synergistically learn are not well understood. Hence, this proposal aims to investigate how the brain learns when the machine undergoes different degrees of learning, how different degrees of brain learning affect long-term BMI performance, robustness, and generalization, and how these principles can guide the design of a 2-learner BMI system which facilitates brain learning. The proposal is structured in three aims: 1) To study the impact of decoder adaptation on the development of neural encoding models underlying neuroprosthetic skill; 2) To Study how decoder adaptation and resultant neural encoding model influences BMI performance with perturbations (robustness) and BMI performance on unpracticed tasks (generalization); and 3) Design and validation of the next-generation Flexible 2-Learner Decoder architecture. The analyses and experiments proposed in these aims will leverage the fundamental knowledge gained about how the brain learns and acquires neuroprosthetic skills into the neurophysiologically-informed design of robust and high-performance closed-loop motor neuroprosthetics that generalize to new tasks.

项目摘要 该建议旨在阐明神经假体技能学习的计算和神经基础， 利用闭环脑机接口科学和工程的最新进展。的 拟议工作的成果有可能指导下一代的发展， 用于神经系统疾病患者的神经生理学信息、皮质控制的神经假体系统 紊乱最先进的脑机接口（BMI）利用机器学习快速校准到 个体的神经活动，但性能也受益于受试者学习可靠地产生所需的 神经活动模式设计这样一个“2-learner BMI”的基本科学和工程原理， 大脑和机器协同学习的知识还没有得到很好的理解。因此，这项建议旨在 研究当机器经历不同程度的学习时，大脑如何学习， 大脑学习的程度影响长期的BMI表现，鲁棒性和概括性，以及这些如何 这些原则可以指导促进大脑学习的2-学习者BMI系统的设计。该提案 本研究的目的有三：1）研究解码器适应对神经编码发展的影响 研究解码器的适应性和由此产生的神经编码 模型影响BMI表现与扰动（鲁棒性）和BMI表现对未经实践的任务 （泛化）;以及3）下一代灵活2学习者解码器架构的设计和验证。 在这些目标中提出的分析和实验将利用所获得的关于以下方面的基本知识： 大脑如何学习和获得神经假体技能， 以及适用于新任务的高性能闭环运动神经修复术。