让神经元有不同反应速度，让训练更稳且效果不差
Heterogeneous Time Constants Improve Stability in Equilibrium Propagation
- 给每个神经元分配不同的时间常数，模拟生物差异
- 训练稳定性显著提升，任务表现仍保持竞争力
- 适合关注生物启发模型与训练鲁棒性的研究者
平衡传播（EP）是一种生物上合理的神经网络训练替代方法，但现有模型采用统一的标量时间步长 dt，这在生物学上并不合理，因为膜时间常数在神经元间是异质的。本文通过从生物驱动分布中为每个神经元分配特定的时间常数，引入了异质时间步长（HTS）的EP方法。结果表明，HTS在保持竞争性任务性能的同时显著提升了训练稳定性。这些发现表明，引入异质时间动态不仅能增强平衡传播的生物合理性，还能提高其鲁棒性。
原文摘要 · Abstract (English)
Equilibrium propagation (EP) is a biologically plausible alternative to backpropagation for training neural networks. However, existing EP models use a uniform scalar time step dt, which corresponds biologically to a membrane time constant that is heterogeneous across neurons. Here, we introduce heterogeneous time steps (HTS) for EP by assigning neuron-specific time constants drawn from biologically motivated distributions. We show that HTS improves training stability while maintaining competitive task performance. These results suggest that incorporating heterogeneous temporal dynamics enhances both the biological realism and robustness of equilibrium propagation.
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。