English(EN) Power-Performance Characterization of TinyML Systems

TinyML系统性能与功耗特征详解

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-25 04:00

本文详细分析了部署在微控制器上的TinyML系统的性能和功耗。研究探讨了在神经网络模型、软件库、操作系统和硬件架构等不同抽象层之间的可编程性与效率之间的权衡。该研究提出了一个量化这些层相关成本的模型，并为优化提供了建议，旨在协助设计人员进行边缘设备的神经架构搜索和CNN推理优化。 AI

影响为优化边缘设备的ML推理提供了见解，有望提高嵌入式AI应用的效率和性能。

排序理由该条目是一篇学术论文，详细介绍了关于TinyML系统的研究结果。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 2 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目是一篇学术论文，详细介绍了关于TinyML系统的研究结果。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 1 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Yujie Zhang, Dhananjaya Wijerathne, Zhaoying Li, Tulika Mitra · 2026-08-25 04:00

TinyML系统的功耗-性能表征

arXiv:2608.21646v1 Announce Type: cross Abstract: TinyML systems are enabling machine learning (ML) inference at the edge. However, there is little quantitative analysis of such systems. This paper presents a systematic performance and power characterization of diverse TinyML app…