实现混合信号芯片上的反馈控制优化器，支持神经形态设备在线学习。
Mixed-signal implementation of feedback-control optimizer for single-layer Spiking Neural Networks
- 采用反馈控制机制在混合信号芯片上实现在线训练
- 在二分类和非线性燕尾问题上达到仿真性能水平
- 适合追求自适应神经形态计算的硬件研究者
片上学习是可扩展、自适应神经形态系统的关键，但现有训练方法要么难以在硬件上实现，要么过于受限。最近研究表明，反馈控制优化器可实现表达性强的片上训练。本文提出一种基于混合信号神经形态处理器的反馈控制优化器概念验证实现。我们在闭环（ITL）训练设置下，针对二分类任务和非线性燕尾问题评估该方法，证明其片上训练性能与数值仿真及基于梯度的基线相当。结果表明，在真实混合信号约束下，反馈驱动的在线学习具有可行性，代表了一种将学习规则直接嵌入硅片的协同设计路径，为自主自适应神经形态计算提供支持。
原文摘要 · Abstract (English)
On-chip learning is key to scalable and adaptive neuromorphic systems, yet existing training methods are either difficult to implement in hardware or overly restrictive. However, recent studies show that feedback-control optimizers can enable expressive, on-chip training of neuromorphic devices. In this work, we present a proof-of-concept implementation of such feedback-control optimizers on a mixed-signal neuromorphic processor. We assess the proposed approach in an In-The-Loop(ITL) training setup on both a binary classification task and the nonlinear Yin-Yang problem, demonstrating on-chip training that matches the performance of numerical simulations and gradient-based baselines. Our results highlight the feasibility of feedback-driven, online learning under realistic mixed-signal constraints, and represent a co-design approach toward embedding such rules directly in silicon for autonomous and adaptive neuromorphic computing.
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。