标题： 面向学习理论的尖峰时间依赖可塑性分析 显示英文标题

标题： Towards a learning-theoretic analysis of spike-timing dependent plasticity

摘要： 本文从学习理论的角度提出了突触可塑性如何有益于全局脑功能的观点。 我们引入了一个模型，称为选择子，它（i）作为具有脉冲时间依赖可塑性（STDP）的漏电积分与发放神经元的快速时间常数极限出现，并且（ii）易于进行理论分析。 我们证明选择子将奖励估计编码为脉冲，并且脉冲的误差界由脉冲间隔和突触权重的总和控制。 此外，脉冲的效果（它们对其他以奖励最大化为目标的选择子的有用性）也取决于总的突触强度。 最后，基于我们的分析，我们提出了一种STDP的正则化版本，并表明当面对多种刺激时，正则化可以提高神经元学习的鲁棒性。 显示英文摘要

摘要： This paper suggests a learning-theoretic perspective on how synaptic plasticity benefits global brain functioning. We introduce a model, the selectron, that (i) arises as the fast time constant limit of leaky integrate-and-fire neurons equipped with spiking timing dependent plasticity (STDP) and (ii) is amenable to theoretical analysis. We show that the selectron encodes reward estimates into spikes and that an error bound on spikes is controlled by a spiking margin and the sum of synaptic weights. Moreover, the efficacy of spikes (their usefulness to other reward maximizing selectrons) also depends on total synaptic strength. Finally, based on our analysis, we propose a regularized version of STDP, and show the regularization improves the robustness of neuronal learning when faced with multiple stimuli.