一个带有持续本地学习的尖端神经网络,用于强大的在线脑机界面
Elijah A Taeckens1, Sahil Shah1
1Department of Electrical and Computer Engineering, University of Maryland, College Park, United States of America.
Journal of neural engineering
|January 4, 2024
概括
针对尖端神经网络 (SNN) 的新型持续学习算法使大脑机器接口 (BMI) 能够在不间断的情况下进行训练,显著减少内存使用量,并适应不断变化的神经环境.
科学领域:
- 计算神经科学是一种神经科学.
- 机器学习 机器学习
- 生物医学工程 生物医学工程
背景情况:
- 尖端神经网络 (SNN) 为脑机界面 (BMI) 提供计算效率和生物可信性.
- 现有的SNN训练方法需要大量的内存,并且无法处理连续的输入流,而无需定期中断反向传播.
- 持续,不间断的训练对于理想的BMI来说至关重要,以尽量减少用户的干扰,并适应动态的神经环境.
研究的目的:
- 为回归学习开发一个连续的SNN重量更新算法.
- 消除存储过去的spiking事件的需要,从而减少内存需求.
- 在真实世界的神经数据和模拟的闭环BMI设置中评估算法的性能.
主要方法:
- 提出了一种新的连续SNN重量更新算法,使回归学习成为可能.
- 实现了算法,不需要对过去的spiking事件进行内存,实现了持续的内存使用.
- 在实现任务和在模拟闭环环境中对灵长类前运动皮层神经记录的SNN进行了评估.
主要成果:
- 实现了与线下训练方法相比的峰值相关性 (ρ=0.7),同时减少了92%的内存使用.
- 在闭环模拟中证明了最先进的准确性.
- 展示了对神经输入干扰的适应能力和成功的在线培训,没有先前的线下培训.
结论:
- 开发的持续学习SNN提供了适合闭环BMI应用的快速神经解码算法.
- 这种算法提高了用户的适应速度,并以最小的干扰适应神经行为变化.
- 这些发现为更具响应性和用户友好的脑机界面铺平了道路.
相关概念视频
Neural Regulation
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
Neural Circuits
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...


