AI 中文总结
针对分布式神经形态系统中通信含拜占庭发送方标签的近似共识问题，提出容错脉冲时间接口\f\f\f，结合多技术保障一致性，满足特定条件下的鲁棒性与低分歧，经仿真与实验验证有效。
AI 中文摘要
大型神经形态系统包含多个处理单元，这些单元可能会复制共享控制参数（如阈值参考值）。若这些副本出现偏差，相同输入将在不同预期设置下被处理。我们研究当通信仅携带带标签的脉冲时间且最多有\f\f\f个发送方标签为拜占庭时，处理单元如何减少这种分歧。原始事件流无法提供经典近似共识所需的每个发送方一个值的输入，因为故障发送方可能保持沉默、向接收方发送大量脉冲，或向不同接收方报告不同时间。我们引入故障脉冲时间接口（\textbackslash SIF），其结合了 paced epochs、发送方归属、每标签首次脉冲（\textbackslash FirstSpike）接纳、有界时序误差和沉默哨兵。对于仿射单脉冲编码，中点解码可达到精确的确定性极小极大误差\rho=\text{min}\{1/2,\text{omega}/L\}，其中\f\f\f是剩余时序不确定性，\f\f\f是可用编码窗口。\textbackslash SpikeTrim将经典的均值子序列约简（MSR）规则应用于按发送方索引的解码值。当\f\f\f≥3\f\f\f+1时，它保证一步鲁棒有效性、直接更新下的紧致无噪收缩因子\f\f\f/(\f\f\f-2\f\f\f\f)、显式最坏情况渐近分歧界，以及瞬态共识状态损坏后的有限恢复。闭式测试可确定经验证的时序预算是否满足目标分歧。仿真展示了故障阈值、时序依赖性、抗洪泛性和恢复能力。受控脉冲分类器实验显示，在有限维护预算下，更快的控制状态对齐与更低的预测分歧相关联。
英文摘要
Large neuromorphic systems contain many processing tiles that may replicate a shared control parameter such as a threshold reference. If these copies diverge, identical inputs may be processed under different intended settings. We study how tiles can reduce this disagreement when communication carries only labeled spike times and up to \(f\) sender labels may be Byzantine. A raw event stream cannot supply the one-value-per-sender input required by classical approximate agreement because a faulty sender can remain silent, flood a receiver, or report different times to different receivers. We introduce the Spike-time Interface for Faults, or \SIF, which combines paced epochs, sender attribution, per-label \FirstSpike admission, bounded timing error, and a silence sentinel. For an affine one-spike code, midpoint decoding attains the exact deterministic minimax error \(ρ=\min\{1/2,ω/L\}\), where \(ω\) is the residual timing uncertainty and \(L\) is the usable encoding window. \SpikeTrim applies the classical mean-subsequence-reduced (MSR) rule to the sender-indexed decoded values. For \(n\ge3f+1\), it guarantees one-step robust validity, the tight noiseless contraction factor \(f/(n-2f)\) under direct updates, an explicit worst-case asymptotic disagreement bound, and finite recovery after transient agreement-state corruption. A closed-form test determines whether a validated timing budget meets a target disagreement. Simulations illustrate the fault threshold, timing dependence, flooding resistance, and recovery. A controlled spiking classifier experiment shows an association between faster control-state alignment and lower prediction disagreement under a finite maintenance budget.
