用生物启发的局部学习实现手写数字识别，精度接近传统方法。
Reward-Modulated Local Learning in Spiking Encoders: Controlled Benchmarks with STDP and Hybrid Rate Readouts
- 设计两种基于脉冲的局部学习机制，结合奖励调制与速率读出。
- 混合模型达86.39%±4.75%准确率，最优配置下提升至95.52%±1.11%。
- 揭示奖励调制与归一化对结果的关键影响，适合神经形态计算研究者。
本文开展了一项受生物学启发的局部学习在手写数字识别中的控制性实证研究。评估了基于脉冲时序依赖可塑性（STDP）的竞争代理模型和基于同一脉冲种群编码器的实用混合基准。代理模型源自具有三因子延迟奖励调制的漏电整合-发放兴奋/抑制电路模型；混合更新在前馈与后馈速率上是局部的，但使用监督标签且不依赖时间信用分配。在sklearn digits数据集上，固定种子测试显示经典像素基线准确率从98.06%提升至98.22%，而局部脉冲模型达到86.39%±4.75%（混合默认）和87.17%±3.74%（STDP风格竞争代理）。消融实验表明归一化和奖励调制设置是最强影响因素，最优混合配置达95.52%±1.11%。无网络合成时间基准支持相同的时间-速率解释。2x2分析进一步显示，奖励调制效果可在不同稳定化区间反转符号，因此奖励调制结论应与归一化设置共同报告。
原文摘要 · Abstract (English)
This paper presents a controlled empirical study of biologically motivated local learning for handwritten digit recognition. We evaluate an STDP-inspired competitive proxy and a practical hybrid benchmark built on the same spiking population encoder. The proxy is motivated by leaky integrate-and-fire E/I circuit models with three-factor delayed reward modulation. The hybrid update is local in pre x post rates but uses supervised labels and no timing-based credit assignment. On sklearn digits, fixed-seed evaluation shows classical pixel baselines from 98.06 to 98.22% accuracy, while local spike-based models reach 86.39 +/- 4.75% (hybrid default) and 87.17 +/- 3.74% (STDP-style competitive proxy). Ablations identify normalization and reward-shaping settings as the strongest observed levers, with a best hybrid ablation of 95.52 +/- 1.11%. A network-free synthetic temporal benchmark supports the same timing-versus-rate interpretation under matched local-update training. A descriptive 2x2 analysis further shows reward-shaping effects can reverse sign across stabilization regimes, so reward-shaping conclusions should be reported jointly with normalization settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。