发表机构
Martin Andrews（Martin Andrews）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究证明STDP$^+$和稳态可塑性两个局部突触学习规则可实现SIGReg自监督学习目标的精确梯度，无需梯度计算等。在合成聚类任务和时间有序MNIST上验证，显示该机制能端到端起作用，如合成任务中有序呈现使聚类分离率大幅提升，MNIST网络取得较高线性探测准确率。
AI 中文摘要
我们证明了两个典型的局部突触学习规则，即依赖于脉冲时间的可塑性（STDP$^+$）的增强臂和稳态可塑性（通过类似手电筒颗粒细胞的神经元实例化），共同可以实现类SIGReg自监督学习目标的精确梯度。这种等效性不需要梯度计算、全局误差信号、权重传输和标签信息：唯一的输入是突触前和突触后的发放率、局部发放统计以及自然感觉流的时间连续性。在一个旨在探究是否仅从输入的时间顺序就能恢复类结构的合成聚类任务中，有序呈现将聚类分离率（CSR）提高到2.49，而随机排序使其接近基线（0.83），这一约三倍（$\approx 3.5\sigma$）的分离仅归因于输入顺序。在时间有序的MNIST上，完全使用这些规则训练的两层网络实现了87.3%的线性探测准确率，表明该机制端到端起作用。
英文摘要
We prove that two canonical local synaptic learning rules, the potentiation arm of spike-timing-dependent plasticity (STDP$^+$) and homeostatic plasticity (instantiated here via flashlight granule-cell-like neurons), together can implement the exact gradient of a SIGReg-like self-supervised learning objective. The equivalence requires no gradient calculations, no global error signals, no weight transport, and no label information: the only inputs are pre- and post-synaptic firing rates, local firing statistics, and the temporal contiguity of natural sensory streams. On a synthetic clustering task designed to probe whether class structure can be recovered from temporal ordering of inputs alone, ordered presentation raised cluster separation (CSR) to 2.49 while random ordering left it near baseline (0.83), a roughly threefold ($\approx 3.5σ$) separation attributable solely to input ordering. On temporally ordered MNIST, a two-layer network trained entirely with these rules achieved 87.3% linear-probe accuracy, showing that the mechanism functions end-to-end.
Comments10 pages, 1 figure. Associated code at https://github.com/mdda/biological-sigreg
