发表机构
Missouri University of Science and Technology; Argonne National Laboratory（密苏里科技大学; 阿贡国家实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出锁定平衡传播（LIEP）原位训练算法，为振荡硬件提供局部梯度，支持从头训练及扰动恢复，并可作为三因子更新规则，有望扩展至深层大规模网络。
AI 中文摘要
模拟硬件平台有潜力降低数字架构的能耗，但为了成功，大规模模拟系统还必须能够在其组件变异性下运行或从中恢复。为此，我们推导并演示了锁定平衡传播（LIEP）训练方法。LIEP为振荡网络中的每个组件提供局部梯度信息，无需单独的前向和反向扫描，从而可能在模拟振荡硬件平台上实现原位学习能力。我们证明LIEP既可用于从头训练，也可用于在预训练参数受到扰动时恢复性能。我们表明LIEP可以表述为三因子更新规则，并建议尽管该方法目前仅在浅层网络上得到验证，但替代架构可能使其扩展到处理复杂任务的深层和大规模网络。
英文摘要
Analog hardware platforms offer the potential to reduce energy consumption over digital architectures, but in order to succeed, large-scale analog systems must also be able to operate with or recover from the variability of their components. Towards this goal, we derive and demonstrate the lock-in equilibrium propagation (LIEP) training method. LIEP provides local gradient information for each component in an oscillatory network without separate forward and backward sweeps, potentially allowing for in-situ learning capabilities on analog oscillatory hardware platforms. We demonstrate that LIEP can be used both for ab-initio training as well as recovering performance when pre-trained parameters are perturbed. We show that LIEP can be formulated as a three-factor update rule, and suggest that although the method is currently only validated on shallow networks, alternate architectures may allow it to extend to deep and large-scale networks addressing complex tasks.
