PulseAugur
中
实时 07:27:17
English(EN) PERTINENCE: Input-based Opportunistic Neural Network Dynamic Execution

PERTINENCE 方法通过动态选择模型优化 DNN 效率

作者 PulseAugur 编辑部 · [1 个来源] ·

研究人员开发了 PERTINENCE，一种新颖的运行时方法，旨在优化深度神经网络 (DNN) 的计算效率。该技术根据输入复杂度从预训练模型集中动态选择最合适的模型，旨在降低计算成本和能耗，同时不显著影响准确性。在包括图像分类和基于 YOLO 的系统在内的各种数据集和应用上的评估表明，PERTINENCE 可以实现相当或更高的准确性，同时将操作减少高达 36%。 AI

影响 该方法可能导致更高效的 AI 部署，降低推理任务的硬件要求和能耗。

排序理由 详细介绍一种优化神经网络执行新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

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

PERTINENCE 方法通过动态选择模型优化 DNN 效率

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
详细介绍一种优化神经网络执行新方法的学术论文。[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
74 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · Omkar Shende, Gayathri Ananthanarayanan, Marcello Traiola ·

    PERTINENCE：基于输入的机遇性神经网络动态执行

    arXiv:2507.01695v3 Announce Type: replace Abstract: Deep neural networks (DNNs) are widely used for their ability to model complex patterns across domains such as computer vision, speech recognition, and robotics. However, larger models, while often more accurate, are computation…

相关实体

相关话题