中文标题#
突触束理论用于脉冲驱动的感知运动系统：超过八个独立的突触束会坍缩奖励 - STDP 学习
英文标题#
Synaptic bundle theory for spike-driven sensor-motor system: More than eight independent synaptic bundles collapse reward-STDP learning
中文摘要#
神经元尖峰直接驱动肌肉，使动物具有敏捷的运动能力，但将基于尖峰的控制信号应用于人工传感 - 运动系统中的执行器不可避免地会导致学习崩溃。 我们开发了一个系统，可以在感觉 - 运动连接中变化 \emph {独立突触束的数量}。 本文展示了以下四个发现：(i) 一旦运动神经元的数量或独立突触束的数量超过临界极限，学习就会崩溃。 (ii) 运动神经元数量较少会增加学习失败的概率，而 (iii) 如果学习成功，运动神经元数量较少会导致更快的学习。 (iv) 与最优权重方向相反的权重更新次数可以定量解释这些结果。 尖峰的功能仍大多未知。 确定使用尖峰的学习系统可以构建的参数范围，将有可能研究之前由于学习困难而无法研究的尖峰功能。
英文摘要#
Neuronal spikes directly drive muscles and endow animals with agile movements, but applying the spike-based control signals to actuators in artificial sensor-motor systems inevitably causes a collapse of learning. We developed a system that can vary \emph{the number of independent synaptic bundles} in sensor-to-motor connections. This paper demonstrates the following four findings: (i) Learning collapses once the number of motor neurons or the number of independent synaptic bundles exceeds a critical limit. (ii) The probability of learning failure is increased by a smaller number of motor neurons, while (iii) if learning succeeds, a smaller number of motor neurons leads to faster learning. (iv) The number of weight updates that move in the opposite direction of the optimal weight can quantitatively explain these results. The functions of spikes remain largely unknown. Identifying the parameter range in which learning systems using spikes can be constructed will make it possible to study the functions of spikes that were previously inaccessible due to the difficulty of learning.
文章页面#
突触束理论用于脉冲驱动的感知运动系统：超过八个独立的突触束会坍缩奖励 - STDP 学习
PDF 获取#
抖音扫码查看更多精彩内容