English(EN) Quantum Tunneling-Aware Machine Learning: Physics-Derived Noise Models for Robust Deployment

新AI方法解决晶体管中的量子隧穿错误

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-30 14:21

研究人员开发了一种名为量子隧穿感知机器学习（QTAML）的新方法，以解决由晶体管中量子隧穿引起的AI推理错误。该方法从第一性原理推导噪声模型，捕获通用模型遗漏的特定错误结构。QTAML利用隧穿感知补偿（TAC）算法来纠正这些错误，其开销远低于现有方法，有望在未来硬件上实现更稳健的AI部署。 AI

影响通过减轻晶体管中量子隧穿引起的错误，在未来硬件上实现更稳健的AI推理。

排序理由该集群包含一篇详细介绍新机器学习方法的学术论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv stat.ML TIER_1 English(EN) · Uiwon Hwang, Jaeho Hwang · 2026-06-02 04:00

量子隧穿感知机器学习：物理推导的噪声模型用于稳健部署

arXiv:2606.00741v1 Announce Type: cross Abstract: Transistor scaling is approaching a quantum-mechanical limit, as thin gate oxides induce electron leakage through quantum tunneling. Unlike conventional digital systems, AI inference can tolerate such errors provided their structu…
arXiv stat.ML TIER_1 English(EN) · Jaeho Hwang · 2026-05-30 14:21

Quantum Tunneling-Aware Machine Learning: Physics-Derived Noise Models for Robust Deployment

Transistor scaling is approaching a quantum-mechanical limit, as thin gate oxides induce electron leakage through quantum tunneling. Unlike conventional digital systems, AI inference can tolerate such errors provided their structure is modeled correctly. In this paper, we introdu…