V2EX weak-supervision

Weak Supervision

释义 Definition

弱监督(学习):一种机器学习训练方式,使用不完全、不精确、带噪声或间接的标注信号来训练模型,而不是依赖大量高质量的人工精标数据。常见信号包括:启发式规则、远程监督(用知识库自动对齐)、弱标注、众包粗标、数据编程的标注函数等。(也常写作 weakly supervised learning。)

发音 Pronunciation (IPA)

/wik suprvn/

例句 Examples

Weak supervision helps us train a model without labeling every image by hand.
弱监督让我们不必为每张图片都手工标注,也能训练模型。

Using weak supervision from heuristics and noisy logs, the team built a classifier that generalized well to new data.
团队利用来自启发式规则和带噪日志的弱监督训练分类器,并在新数据上取得了较好的泛化效果。

词源 Etymology

weak 来自古英语 wāc,表示“软弱的、力量不足的”,在此引申为“信号强度不够、可靠性不高”。supervision 源自拉丁语 *super-*(“在上、之上”)+ videre(“看”),原义接近“监督、看管”。合起来在机器学习语境中指:监督信号“有但不强/不干净”,并非完全准确的真值标注。

相关词 Related Words

  • Distant Supervision
  • Semi-Supervised Learning
  • Self-Supervised Learning
  • Noisy Labels
  • Labeling Function
  • Data Programming
  • Active Learning
  • Transfer Learning
  • 文献与作品 Literary / Notable Works

    • Snorkel: Rapid Training Data Creation with Weak Supervision(系统阐述用弱监督/标注函数快速生成训练数据的代表性论文与方法)
    • Data Programming: Creating Large Training Sets, Quickly(介绍以“数据编程”方式组织弱监督信号的经典工作)
    • Deep Learning(Ian Goodfellow, Yoshua Bengio, Aaron Courville)(书中在监督学习相关章节与扩展讨论里常提及弱标注/噪声标注等与弱监督紧密相关的设定)
    • Foundations of Machine Learning(在学习理论与噪声、标注不完美等话题中,与弱监督问题域高度相关)
    关于     帮助文档     自助推广系统     博客     API     FAQ     Solana     2633 人在线   最高记录 6679       Select Language
    创意工作者们的社区
    World is powered by solitude
    VERSION: 3.9.8.5 50ms UTC 05:01 PVG 13:01 LAX 22:01 JFK 01:01
    Do have faith in what you're doing.
    ubao msn snddm index pchome yahoo rakuten mypaper meadowduck bidyahoo youbao zxmzxm asda bnvcg cvbfg dfscv mmhjk xxddc yybgb zznbn ccubao uaitu acv GXCV ET GDG YH FG BCVB FJFH CBRE CBC GDG ET54 WRWR RWER WREW WRWER RWER SDG EW SF DSFSF fbbs ubao fhd dfg ewr dg df ewwr ewwr et ruyut utut dfg fgd gdfgt etg dfgt dfgd ert4 gd fgg wr 235 wer3 we vsdf sdf gdf ert xcv sdf rwer hfd dfg cvb rwf afb dfh jgh bmn lgh rty gfds cxv xcv xcs vdas fdf fgd cv sdf tert sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf shasha9178 shasha9178 shasha9178 shasha9178 shasha9178 liflif2 liflif2 liflif2 liflif2 liflif2 liblib3 liblib3 liblib3 liblib3 liblib3 zhazha444 zhazha444 zhazha444 zhazha444 zhazha444 dende5 dende denden denden2 denden21 fenfen9 fenf619 fen619 fenfe9 fe619 sdf sdf sdf sdf sdf zhazh90 zhazh0 zhaa50 zha90 zh590 zho zhoz zhozh zhozho zhozho2 lislis lls95 lili95 lils5 liss9 sdf0ty987 sdft876 sdft9876 sdf09876 sd0t9876 sdf0ty98 sdf0976 sdf0ty986 sdf0ty96 sdf0t76 sdf0876 df0ty98 sf0t876 sd0ty76 sdy76 sdf76 sdf0t76 sdf0ty9 sdf0ty98 sdf0ty987 sdf0ty98 sdf6676 sdf876 sd876 sd876 sdf6 sdf6 sdf9876 sdf0t sdf06 sdf0ty9776 sdf0ty9776 sdf0ty76 sdf8876 sdf0t sd6 sdf06 s688876 sd688 sdf86