CINXE.COM
监督学习 - 标签 - 腾讯云开发者社区-腾讯云
<!DOCTYPE html><html munual-autotracker-init="" qct-pv-id="-lXvC4Vb85AZDSwd6q4_4" qct-ip="8.222.208.146"><head><meta charSet="UTF-8"/><meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1"/><title>监督学习 - 标签 - 腾讯云开发者社区-腾讯云</title><meta name="keywords" content="监督学习,云+社区标签"/><meta name="subjectTime" content="2018-09-06 18:31:33"/><meta name="description" content="监督式学习，是一个机器学习中的方法，可以由训练资料中学到或建立一个模式，并依此模式推测新的实例。"/><meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1, viewport-fit=cover"/><meta name="format-detection" content="telephone=no"/><link rel="canonical" href="https://cloud.tencent.com/developer/tag/10719"/><link rel="stylesheet" href="//cloudcache.tencent-cloud.cn/open_proj/proj_qcloud_v2/gateway/portal/css/global-20209142343.css"/><link rel="stylesheet" href="//cloudcache.tencent-cloud.cn/qcloud/ui/cloud-community/build/base/base-202410111735.css"/><link rel="stylesheet" href="//cloudcache.tencent-cloud.cn/open_proj/proj_qcloud_v2/community-pc/build/AskDialog/AskDialog-202204021635.css?max_age=31536000"/><link rel="stylesheet" href="//cloudcache.tencent-cloud.cn/open_proj/proj_qcloud_v2/community-pc/build/AskDialog/AskDialog-202204021635.css?max_age=31536000"/><link rel="stylesheet" href="//cloudcache.tencent-cloud.cn/qcloud/ui/community-pc/build/base/base-202412201223.css"/><link rel="stylesheet" href="//cloudcache.tencent-cloud.cn/qcloud/ui/cloud-community/build/base/base-202410111735.css"/><link rel="stylesheet" href="//cloudcache.tencent-cloud.cn/open_proj/proj_qcloud_v2/community-pc/build/Tag/Tag-202105140928.css?max_age=31536000"/><link rel="stylesheet" href="//cloudcache.tencent-cloud.cn/open_proj/proj_qcloud_v2/community/portal/css/markdown-201810241044.css?max_age=31536000"/><link rel="stylesheet" href="//cloudcache.tencent-cloud.cn/qcloud/draft-master/dist/draft-master-v2.0.165.d4s2ddo9sb.css?max_age=31536000"/><style media="screen">@supports (padding:max(0px)){.set-safe-area .com-main{bottom:calc(max(12px,constant(safe-area-inset-bottom)) + 50px);bottom:calc(max(12px,env(safe-area-inset-bottom)) + 50px)}.set-safe-area .com-main-simple-sec,.set-safe-area .com-main.without-tab-ft,.set-safe-area .com-main.without-ft{bottom:max(12px,constant(safe-area-inset-bottom));bottom:max(12px,env(safe-area-inset-bottom))}.set-safe-area .com-main-sec{bottom:max(12px,constant(safe-area-inset-bottom));bottom:max(12px,env(safe-area-inset-bottom))}.set-safe-area .com-m-footer,.set-safe-area .sa-fixed-btns{bottom:max(12px,constant(safe-area-inset-bottom));bottom:max(12px,env(safe-area-inset-bottom))}.set-safe-area .com-mobile-body{bottom:max(12px,constant(safe-area-inset-bottom));bottom:max(12px,env(safe-area-inset-bottom))}}@supports (padding:max(0px)){.set-safe-area .support-wrap,.set-safe-area div.body{bottom:max(12px,constant(safe-area-inset-bottom));bottom:max(12px,env(safe-area-inset-bottom))}.set-safe-area .com-responsive-no-ft div.body{bottom:max(12px,constant(safe-area-inset-bottom));bottom:max(12px,env(safe-area-inset-bottom))}}.doc-con .J-docShareModal{display: none;} .doc-con .J-docShareCopyTipModalMB{display: none} .with-focus+.com-main-simple-sec, .with-focus+.com-main,.with-focus+.com-body,.with-focus+.qa-body{top:100px} .qa-detail-ask-panel:after{display:none!important;} .sa-fixed-btns .c-btn-weak{background-color: #fff;} .qa-r-editor.draft-editor-host.rno-markdown{height: 290px;overflow-y:auto;} .uc-achievement{line-height:24px;margin-bottom:5px;white-space: initial;overflow:visible;text-overflow:initial} .uc-achievement .uc-achievement-icon{top:0;margin-top:0;}</style></head><body style="position:initial"><div id="react-root" class=""><div class="comp-tag-detail"><div class="cdc-header is-fixed"><div class="cdc-header__placeholder"></div><div class="cdc-header__inner"><div class="cdc-header__top"><div class="cdc-header__top-left"><a href="/?from=20060&from_column=20060" target="_blank" class="cdc-header__top-logo"><i>腾讯云</i></a><div class="cdc-header__top-line"></div><a href="/developer" class="cdc-header__top-logo community"><i>开发者社区</i></a><div class="cdc-header__activity"><div id="cloud-header-product-container"></div></div></div><div class="cdc-header__top-operates"><a href="/document/product?from=20702&from_column=20702" target="_blank" class="cdc-header__link">文档</a><a href="/voc/?from=20703&from_column=20703" target="_blank" class="cdc-header__link">建议反馈</a><a href="https://console.cloud.tencent.com?from=20063&from_column=20063" target="_blank" class="cdc-header__link" track-click="{"areaId":102001,"subAreaId":1}">控制台</a><div class="cdc-header__account"><div class="cdc-header__account-inner"><button class="cdc-btn cdc-header__account-btn cdc-btn--primary">登录/注册</button></div></div></div></div><div class="cdc-header__bottom"><div class="cdc-header__bottom-nav"><a href="/developer" class="cdc-header__bottom-home">首页</a><div class="cdc-header__nav-list"><div class="cdc-header__nav-item">学习</div><div class="cdc-header__nav-item">活动</div><div class="cdc-header__nav-item">专区</div><div class="cdc-header__nav-item">工具</div></div><a href="/tvp?from=20154&from_column=20154" class="cdc-header__tvp" target="_blank">TVP</a><div class="cdc-header__activity"><a class="cdc-header__activity-tit" href="/act?from=20061&from_column=20061" target="_blank">最新优惠活动<div class="cdc-badge"><div class="cdc-badge-inner"><div class="cdc-badge-text"></div></div></div></a></div><div id="community-header-product-container"></div></div><div class="cdc-header__bottom-operates"><div class="cdc-header__search"><div class="cdc-search__wrap"><div class="cdc-search"><span class="cdc-search__text">文章/答案/技术大牛</span><button class="cdc-search__btn">搜索<i class="cdc-search__i search"></i></button></div><div class="cdc-search__dropdown"><div class="cdc-search__bar"><input type="text" class="cdc-search__bar-input" placeholder="文章/答案/技术大牛" value=""/><div class="cdc-search__bar-btns"><button class="cdc-search__btn">搜索<i class="cdc-search__i search"></i></button><button class="cdc-search__btn">关闭<i class="cdc-search__i clear"></i></button></div></div></div></div></div><div class="cdc-header__create"><span class="cdc-header__create-btn not-logged"><span class="cdc-svg-icon-con"><span class="cdc-svg-icon" style="line-height:1;color:#0052D9;width:16px;height:16px"><svg width="16" height="16" viewBox="0 0 16 16" fill="currentcolor" xmlns="http://www.w3.org/2000/svg"><path d="M14.2466 12.0145C14.1698 13.6258 12.8381 14.9131 11.2129 14.9131H11.1579H4.0927H4.03772C2.4125 14.9131 1.08014 13.6258 1.00334 12.0145H1V11.8668V4.07213V4.04627V3.89922H1.00334C1.08014 2.28732 2.4125 1 4.03772 1H9.6473V1.00069H10.0786L8.7688 2.10773H8.43888H7.7916H6.37904H4.03772C2.97234 2.10773 2.10445 2.9777 2.10445 4.04629V4.41869V4.4472V6.39498V11.4269V11.4309V11.8668C2.10445 12.9354 2.97234 13.8053 4.03772 13.8053H6.37904H8.87153H11.2129C12.2782 13.8053 13.1461 12.9355 13.1461 11.8668V11.466V11.454V9.5181V6.39364L14.2506 5.3051V11.8668V12.0145H14.2466ZM10.4324 7.15226L9.63146 7.99761C9.36577 8.2693 8.69326 8.95104 8.48066 9.17631C8.26726 9.40288 8.09039 9.58901 7.95061 9.73544C7.81079 9.88188 7.72667 9.96597 7.70083 9.98656C7.63321 10.0488 7.55703 10.1144 7.47022 10.1846C7.38412 10.2542 7.29404 10.3099 7.20063 10.3516C7.10722 10.4007 6.97072 10.459 6.79049 10.5305C6.61028 10.6001 6.42213 10.6676 6.22468 10.7339C6.02792 10.8002 5.84109 10.8571 5.66484 10.9061C5.48795 10.9538 5.3561 10.9863 5.2693 11.0009C5.08977 11.0214 4.96988 10.993 4.90956 10.9168C4.84931 10.8405 4.83276 10.7107 4.85924 10.5312C4.87315 10.4331 4.9043 10.292 4.95468 10.1078C5.00431 9.92297 5.05802 9.7315 5.11431 9.53341C5.1713 9.33526 5.22629 9.15179 5.27926 8.98484C5.33297 8.8179 5.37599 8.7026 5.40978 8.64032C5.44953 8.54357 5.49463 8.45413 5.54495 8.37399C5.59465 8.29379 5.66616 8.20503 5.75965 8.10766C5.79934 8.06588 5.89281 7.96649 6.03988 7.81018C6.18624 7.65311 6.80114 7.02774 7.02104 6.79783L7.75117 6.03524L8.56212 5.1899L10.6345 3.02466L12.5214 4.93874L10.4324 7.15226ZM13.816 3.58581C13.7166 3.68987 13.6272 3.78064 13.5483 3.85883C13.4694 3.93703 13.4006 4.0066 13.3423 4.06686C13.276 4.13643 13.2144 4.19738 13.1561 4.24903L11.2785 2.33569C11.3785 2.24025 11.4965 2.12565 11.6336 1.99115C11.7707 1.85668 11.8854 1.75061 11.9761 1.67242C12.0934 1.57708 12.2133 1.51013 12.3385 1.47109C12.4525 1.43529 12.5644 1.41805 12.6751 1.41876H12.7056C12.7665 1.42139 12.8268 1.42729 12.8851 1.43724C12.8838 1.4366 12.8811 1.43724 12.8798 1.4366C12.8811 1.4366 12.8838 1.4366 12.8851 1.43724C13.1376 1.48428 13.4019 1.62009 13.6265 1.83743C13.7511 1.95871 13.8524 2.09382 13.9259 2.23296C14.0346 2.43834 14.0863 2.65304 14.0763 2.8491C14.0763 2.87294 14.0783 2.89748 14.0783 2.92201C14.0783 3.03529 14.0571 3.14789 14.0154 3.26055C13.9737 3.37314 13.9067 3.48185 13.816 3.58581Z" fill="#0052D9"></path></svg></span></span>发布<span class="cdc-svg-icon-con cdc-header__create-btn-arrow"><span class="cdc-svg-icon" style="line-height:1;color:inherit;width:16px;height:16px"><svg width="16" height="16" viewBox="0 0 16 16" fill="currentcolor" xmlns="http://www.w3.org/2000/svg"><path d="M8.16377 4L9.57798 5.41421L14.5277 10.364L13.1135 11.7782L8.1638 6.829L3.21402 11.7782L1.7998 10.364L8.16377 4Z"></path></svg></span></span></span></div></div></div></div></div><div class="cdc-m-header with-focus is-fixed"><div class="cdc-m-header__placeholder"></div><div class="cdc-m-header__inner"><div class="cdc-m-guider-banner is-sticky"><div class="cdc-m-guider-banner__guide-mvp" track-exposure="{"areaId":118000}" track-click="{"areaId":118000}"><div class="cdc-m-guider-banner__guide-mvp-text">精选内容/技术社群/优惠产品,<em>尽在小程序</em></div><div class="cdc-m-guider-banner__guide-mvp-btn">立即前往</div></div></div><div class="cdc-m-header__main"><div class="cdc-m-header__trigger"></div><div class="cdc-m-header__logo"><i class="cdc-m-header__logo-icon"></i></div><div class="cdc-m-header__search"><i class="cdc-m-header__search-icon"></i></div><div class="cdc-m-header__operate"><span class="cdc-m-header__operate-icon"></span></div></div></div></div><div class="J-body com-body max-width"><div class="com-crumb"><div class="com-inner"><a href="/developer" class="crumb-item">首页</a><span class="crumb-split"></span><a href="/developer/tags" class="crumb-item">标签</a><span class="crumb-split"></span><span class="crumb-item current">监督学习</span></div></div><div track-click="{"areaId":{"areaId":113006}}" track-exposure="{"areaId":{"areaId":113006}}" class="com-tag-intro"><i class="intro-bg"></i><h2 class="intro-title"><em>#</em>监督学习</h2><p class="intro-desc">监督式学习，是一个机器学习中的方法，可以由训练资料中学到或建立一个模式，并依此模式推测新的实例。</p><div class="intro-btns"><button type="button" class="c-btn" track-click="{"elementId":1}">关注</button></div></div><div class="com-2-layout"><div class="layout-main"><div class="com-tab large tag-tab"><div class="com-tab-hd large"><ul class="com-tab-ctrl"><li class="com-tab-item actived"><a href="javascript:;">专栏文章<span class="num">(1.9K)</span></a></li><li class="com-tab-item"><a href="/developer/tag/10719?entry=video">技术视频<span class="num">(0)</span></a></li><li class="com-tab-item"><a href="/developer/tag/10719?entry=ask">互动问答<span class="num">(10)</span></a></li></ul></div><div class="com-tab-bd"><div class="com-tab-panel" style="min-height:800px"><div class="com-article-panel-v2-list"><section class="com-article-panel-v2 higher"><a href="/developer/article/2497901" track-click="{"areaId":113001,"objectType":"article","objectId":2497901}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2497901}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">苹果也在蒸馏大模型，给出了蒸馏Scaling Laws</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a><a href="/developer/tag/15852?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":15852}" class="com-tag-v2">scaling</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/17394?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17394}" class="com-tag-v2">苹果</a><a href="/developer/tag/17440?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17440}" class="com-tag-v2">数据</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/455fb5110891e0133dc1784094846036.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/1754229" track-click="{"objectType":"user","objectId":1754229}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://ask.qcloudimg.com/avatar/1754229/32embxnqwf.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/1754229" track-click="{"objectType":"user","objectId":1754229}" target="_blank" class="author-info name">机器之心</a><span class="author-info time"><time dateTime="2025-02-19 23:01:02" title="2025-02-19 23:01:02"> <span>5</span>天前<span class="com-v-box">2025-02-19 23:01:02</span></time></span></div></div></div><p class="com-article-panel-v2-des">该结果表明，当两个学习过程都有足够的数据或计算时，蒸馏不能产生比监督学习更低的模型交叉熵。但是，如果以下两个条件都成立，则蒸馏比监督学习更有效：</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>73</span><span class="com-opt-link link-like"><i class="com-i-like"></i>0</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2497901.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2497052" track-click="{"areaId":113001,"objectType":"article","objectId":2497052}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2497052}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">怎么知道效果提升了？7个用于改进RAG系统的检索指标</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/17506?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17506}" class="com-tag-v2">系统</a><a href="/developer/tag/17525?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17525}" class="com-tag-v2">性能</a><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a><a href="/developer/tag/17390?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17390}" class="com-tag-v2">排序</a><a href="/developer/tag/17440?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17440}" class="com-tag-v2">数据</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-100000/8e0b86e9a455f17074ee8c7d4424643e.png?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/1293914" track-click="{"objectType":"user","objectId":1293914}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/6af473c5f2793c53e00484d0b037754e.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/1293914" track-click="{"objectType":"user","objectId":1293914}" target="_blank" class="author-info name">致Great</a><span class="author-info time"><time dateTime="2025-02-17 18:47:42" title="2025-02-17 18:47:42"> <span>8</span>天前<span class="com-v-box">2025-02-17 18:47:42</span></time></span></div></div></div><p class="com-article-panel-v2-des">准确率通常定义为正确预测的比例（包括真正例和真负例）与总案例数之比。如果你熟悉监督学习中的分类问题，可能已经对这个指标有所了解。在检索和RAG的背景下，它的计算...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>127</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2497052.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2495099" track-click="{"areaId":113001,"objectType":"article","objectId":2495099}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2495099}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">AI应用实战课学习总结（1）必备AI基础理论</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/10333?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10333}" class="com-tag-v2">深度学习</a><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/17440?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17440}" class="com-tag-v2">数据</a><a href="/developer/tag/10149?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10149}" class="com-tag-v2">机器学习</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/bbe5b29842631c99955c097357efe836.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/7499234" track-click="{"objectType":"user","objectId":7499234}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://ask.qcloudimg.com/http-save/yehe-7499234/c96c64adf4850c3af5eb82a172828dcb.jpeg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/7499234" track-click="{"objectType":"user","objectId":7499234}" target="_blank" class="author-info name">郑子铭</a><span class="author-info time"><time dateTime="2025-02-10 19:47:09" title="2025-02-10 19:47:09"> <span>14</span>天前<span class="com-v-box">2025-02-10 19:47:09</span></time></span></div></div></div><p class="com-article-panel-v2-des">由于公司的愿景逐渐调整为ONE Tech Company，公司的IT战略也逐渐地朝着Data & AI Driven发展，因此近半年来我一直在学习大模型相关的东...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>108</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2495099.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2492741" track-click="{"areaId":113001,"objectType":"article","objectId":2492741}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2492741}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">首个公开发表的SAR图像目标识别基础模型！国防科大刘永祥&刘丽教授团队提出SARATR-X 1.0</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/10667?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10667}" class="com-tag-v2">开源</a><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a><a href="/developer/tag/17302?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17302}" class="com-tag-v2">基础</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/17440?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17440}" class="com-tag-v2">数据</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/3e5a6e6a327b059b22a00557fed21bf3.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/1754229" track-click="{"objectType":"user","objectId":1754229}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://ask.qcloudimg.com/avatar/1754229/32embxnqwf.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/1754229" track-click="{"objectType":"user","objectId":1754229}" target="_blank" class="author-info name">机器之心</a><span class="author-info time"><time dateTime="2025-02-03 14:52:46" title="2025-02-03 14:52:46"> <span>22</span>天前<span class="com-v-box">2025-02-03 14:52:46</span></time></span></div></div></div><p class="com-article-panel-v2-des">合成孔径雷达（Synthetic Aperture Radar, SAR）作为一种基于电磁波的主动探测技术，具有全天时、全天候的对地观测能力，已发展成为一种不可...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>210</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2492741.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2491711" track-click="{"areaId":113001,"objectType":"article","objectId":2491711}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2491711}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">AI Vision 2024：CVPR 引爆科技核爆，解锁计算机视觉未来无限可能！</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a><a href="/developer/tag/17310?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17310}" class="com-tag-v2">计算机视觉</a><a href="/developer/tag/17347?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17347}" class="com-tag-v2">科技</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/17440?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17440}" class="com-tag-v2">数据</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/11458826" track-click="{"objectType":"user","objectId":11458826}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/avatar/8826.png?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/11458826" track-click="{"objectType":"user","objectId":11458826}" target="_blank" class="author-info name">用户11458826</a><span class="author-info time"><time dateTime="2025-01-25 19:59:33" title="2025-01-25 19:59:33"> <span>30</span>天前<span class="com-v-box">2025-01-25 19:59:33</span></time></span></div></div></div><p class="com-article-panel-v2-des">随着人工智能（AI）的飞速发展，计算机视觉（CV）已经成为支撑多种AI应用的重要基础。从自动驾驶汽车、面部识别系统到精准医疗影像分析，计算机视觉的技术正在极大地...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>93</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2491711.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2490784" track-click="{"areaId":113001,"objectType":"article","objectId":2490784}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2490784}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">【机器学习-监督学习】朴素贝叶斯</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/17440?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17440}" class="com-tag-v2">数据</a><a href="/developer/tag/10149?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10149}" class="com-tag-v2">机器学习</a><a href="/developer/tag/10490?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10490}" class="com-tag-v2">短信</a><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-100000/c5a078734ef07f3b5710ec4e0a608016.png?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/11457362" track-click="{"objectType":"user","objectId":11457362}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/85f1d5aca973f3d501211269bdba7e3c.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/11457362" track-click="{"objectType":"user","objectId":11457362}" target="_blank" class="author-info name">Francek Chen</a><span class="author-info time"><time dateTime="2025-01-22 23:40:39" title="2025-01-22 23:40:39"> 2025-01-22<span class="com-v-box">2025-01-22 23:40:39</span></time></span></div></div></div><p class="com-article-panel-v2-des"> 贝叶斯分类是一类分类算法的总称，这类算法均以贝叶斯定理为基础，所以统称为贝叶斯分类。朴素贝叶斯是一种贝叶斯分类算法，在许多场合可以与决策树和神经网络分类算法...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>102</span><span class="com-opt-link link-like"><i class="com-i-like"></i>0</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2490784.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2490783" track-click="{"areaId":113001,"objectType":"article","objectId":2490783}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2490783}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">【机器学习-监督学习】集成学习与梯度提升决策树</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/17460?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17460}" class="com-tag-v2">算法</a><a href="/developer/tag/10149?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10149}" class="com-tag-v2">机器学习</a><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a><a href="/developer/tag/10721?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10721}" class="com-tag-v2">决策树</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-11457362/d770866cdf04d54a6c1e60e4629f12b2.png?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/11457362" track-click="{"objectType":"user","objectId":11457362}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/85f1d5aca973f3d501211269bdba7e3c.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/11457362" track-click="{"objectType":"user","objectId":11457362}" target="_blank" class="author-info name">Francek Chen</a><span class="author-info time"><time dateTime="2025-01-22 23:39:41" title="2025-01-22 23:39:41"> 2025-01-22<span class="com-v-box">2025-01-22 23:39:41</span></time></span></div></div></div><p class="com-article-panel-v2-des"> 本文将会首先介绍集成学习的思路以及一些常用的集成学习方法，然后介绍梯度提升决策树模型。在前面的文章中，我们讲解了许多不同的机器学习算法，每个算法都有其独特的...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>123</span><span class="com-opt-link link-like"><i class="com-i-like"></i>0</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2490783.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2490782" track-click="{"areaId":113001,"objectType":"article","objectId":2490782}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2490782}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">【机器学习-监督学习】决策树</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/10149?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10149}" class="com-tag-v2">机器学习</a><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a><a href="/developer/tag/10721?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10721}" class="com-tag-v2">决策树</a><a href="/developer/tag/17440?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17440}" class="com-tag-v2">数据</a><a href="/developer/tag/17460?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17460}" class="com-tag-v2">算法</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-11457362/c8272686ac7a4e44c5c221175404dae8.png?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/11457362" track-click="{"objectType":"user","objectId":11457362}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/85f1d5aca973f3d501211269bdba7e3c.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/11457362" track-click="{"objectType":"user","objectId":11457362}" target="_blank" class="author-info name">Francek Chen</a><span class="author-info time"><time dateTime="2025-01-22 23:30:52" title="2025-01-22 23:30:52"> 2025-01-22<span class="com-v-box">2025-01-22 23:30:52</span></time></span></div></div></div><p class="com-article-panel-v2-des"> 本文开始，我们将介绍机器学习中与神经网络并行的另一大类模型——决策树（decision tree）模型及其变种。决策树模型是非参数化模型。决策树模型简称树模...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>81</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2490782.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2490779" track-click="{"areaId":113001,"objectType":"article","objectId":2490779}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2490779}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">【机器学习-监督学习】神经网络与多层感知机</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/10149?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10149}" class="com-tag-v2">机器学习</a><a href="/developer/tag/10332?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10332}" class="com-tag-v2">神经网络</a><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a><a href="/developer/tag/17290?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17290}" class="com-tag-v2">函数</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-100000/a7dacf9aa3e7171f52746b9e2c6381ff.png?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/11457362" track-click="{"objectType":"user","objectId":11457362}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/85f1d5aca973f3d501211269bdba7e3c.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/11457362" track-click="{"objectType":"user","objectId":11457362}" target="_blank" class="author-info name">Francek Chen</a><span class="author-info time"><time dateTime="2025-01-22 23:24:20" title="2025-01-22 23:24:20"> 2025-01-22<span class="com-v-box">2025-01-22 23:24:20</span></time></span></div></div></div><p class="com-article-panel-v2-des"> 本文将会介绍机器学习中最重要的内容之一——神经网络（neural network，NN），它是深度学习的基础。神经网络的名称来源于生物中的神经元。自有计算机...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>137</span><span class="com-opt-link link-like"><i class="com-i-like"></i>0</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2490779.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2490777" track-click="{"areaId":113001,"objectType":"article","objectId":2490777}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2490777}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">【机器学习-监督学习】双线性模型</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a><a href="/developer/tag/17290?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17290}" class="com-tag-v2">函数</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/17440?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17440}" class="com-tag-v2">数据</a><a href="/developer/tag/10149?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10149}" class="com-tag-v2">机器学习</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-11457362/240b595d4c80e69673e4490b2a24fb60.png?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/11457362" track-click="{"objectType":"user","objectId":11457362}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/85f1d5aca973f3d501211269bdba7e3c.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/11457362" track-click="{"objectType":"user","objectId":11457362}" target="_blank" class="author-info name">Francek Chen</a><span class="author-info time"><time dateTime="2025-01-22 23:18:58" title="2025-01-22 23:18:58"> 2025-01-22<span class="com-v-box">2025-01-22 23:18:58</span></time></span></div></div></div><p class="com-article-panel-v2-des"> 从本文开始，我们介绍参数化模型中的非线性模型。在前几篇文章中，我们介绍了线性回归与逻辑斯谛回归模型。这两个模型都有一个共同的特征：包含线性预测因子</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>76</span><span class="com-opt-link link-like"><i class="com-i-like"></i>0</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2490777.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2490776" track-click="{"areaId":113001,"objectType":"article","objectId":2490776}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2490776}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">【机器学习-监督学习】逻辑斯谛回归</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/10149?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10149}" class="com-tag-v2">机器学习</a><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a><a href="/developer/tag/17290?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17290}" class="com-tag-v2">函数</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/17440?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17440}" class="com-tag-v2">数据</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-11457362/ee73d8c0e1bd433cea97640d471f19c4.png?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/11457362" track-click="{"objectType":"user","objectId":11457362}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/85f1d5aca973f3d501211269bdba7e3c.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/11457362" track-click="{"objectType":"user","objectId":11457362}" target="_blank" class="author-info name">Francek Chen</a><span class="author-info time"><time dateTime="2025-01-22 23:17:11" title="2025-01-22 23:17:11"> 2025-01-22<span class="com-v-box">2025-01-22 23:17:11</span></time></span></div></div></div><p class="com-article-panel-v2-des"> 在介绍了机器学习中相关的基本概念和技巧后，本章我们继续讲解参数化模型中的线性模型。有了前文的基础，我们可以先来对KNN算法和线性回归进行比较，进一步回答“什...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>125</span><span class="com-opt-link link-like"><i class="com-i-like"></i>0</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2490776.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2490407" track-click="{"areaId":113001,"objectType":"article","objectId":2490407}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2490407}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">首个公开发表的SAR图像目标识别基础模型！国防科大刘永祥&刘丽教授团队提出SARATR-X 1.0</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/10667?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10667}" class="com-tag-v2">开源</a><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a><a href="/developer/tag/17302?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17302}" class="com-tag-v2">基础</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/17440?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17440}" class="com-tag-v2">数据</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/a1d54a2dc08e751d32f2960934241461.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/1577869" track-click="{"objectType":"user","objectId":1577869}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://ask.qcloudimg.com/http-save/yehe-1577869/emq6640j7j.jpeg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/1577869" track-click="{"objectType":"user","objectId":1577869}" target="_blank" class="author-info name">计算机视觉研究院</a><span class="author-info time"><time dateTime="2025-01-22 12:41:26" title="2025-01-22 12:41:26"> 2025-01-22<span class="com-v-box">2025-01-22 12:41:26</span></time></span></div></div></div><p class="com-article-panel-v2-des">合成孔径雷达（Synthetic Aperture Radar, SAR）作为一种基于电磁波的主动探测技术，具有全天时、全天候的对地观测能力，已发展成为一种不可...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>99</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2490407.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2488061" track-click="{"areaId":113001,"objectType":"article","objectId":2488061}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2488061}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">一文详尽之Embedding（向量表示）！</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/17440?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17440}" class="com-tag-v2">数据</a><a href="/developer/tag/17554?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17554}" class="com-tag-v2">优化</a><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a><a href="/developer/tag/13234?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":13234}" class="com-tag-v2">embedding</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/bd9132720f8d6a97645c2ca6ed4ca3cc.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/4303953" track-click="{"objectType":"user","objectId":4303953}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://ask.qcloudimg.com/http-save/yehe-4303953/1akvz8h16e.jpeg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/4303953" track-click="{"objectType":"user","objectId":4303953}" target="_blank" class="author-info name">Datawhale</a><span class="author-info time"><time dateTime="2025-01-19 20:01:22" title="2025-01-19 20:01:22"> 2025-01-19<span class="com-v-box">2025-01-19 20:01:22</span></time></span></div></div></div><p class="com-article-panel-v2-des">文本是一类非常重要的非结构化数据，如何表示文本数据一直是机器学习领域的一个重点研究方向。文本向量就是深度学习时代产生的一种文本表示的方法。</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>274</span><span class="com-opt-link link-like"><i class="com-i-like"></i>0</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2488061.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2486288" track-click="{"areaId":113001,"objectType":"article","objectId":2486288}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2486288}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">不需要标注了？看自监督学习框架如何助力目标检测</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a><a href="/developer/tag/17353?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17353}" class="com-tag-v2">框架</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/17525?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17525}" class="com-tag-v2">性能</a><a href="/developer/tag/10147?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10147}" class="com-tag-v2">自动驾驶</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/f9d7ede4a46cf75c51675d5d5997a4cf.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/1577869" track-click="{"objectType":"user","objectId":1577869}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://ask.qcloudimg.com/http-save/yehe-1577869/emq6640j7j.jpeg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/1577869" track-click="{"objectType":"user","objectId":1577869}" target="_blank" class="author-info name">计算机视觉研究院</a><span class="author-info time"><time dateTime="2025-01-12 13:00:45" title="2025-01-12 13:00:45"> 2025-01-12<span class="com-v-box">2025-01-12 13:00:45</span></time></span></div></div></div><p class="com-article-panel-v2-des">论文链接：https://arxiv.org/pdf/2104.08683.pdf</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>120</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2486288.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2485824" track-click="{"areaId":113001,"objectType":"article","objectId":2485824}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2485824}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">时序论文35｜LPTM：用于跨领域时序任务预训练模型（引入动态切分）</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/17440?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17440}" class="com-tag-v2">数据</a><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a><a href="/developer/tag/17303?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17303}" class="com-tag-v2">集合</a><a href="/developer/tag/17373?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17373}" class="com-tag-v2">论文</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/2d98e120e1934df28543ee6cc5f02332.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/4434621" track-click="{"objectType":"user","objectId":4434621}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/d475988d13f7edf01d8a40a916381bb0.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/4434621" track-click="{"objectType":"user","objectId":4434621}" target="_blank" class="author-info name">科学最Top</a><span class="author-info time"><time dateTime="2025-01-09 20:32:39" title="2025-01-09 20:32:39"> 2025-01-09<span class="com-v-box">2025-01-09 20:32:39</span></time></span></div></div></div><p class="com-article-panel-v2-des">首先要知道文中说的SSL loss，SSL 是 Self - Supervised Learning（自监督学习）的缩写，SSL loss 即自监督学习损失。用...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>137</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2485824.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2485372" track-click="{"areaId":113001,"objectType":"article","objectId":2485372}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2485372}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">【机器学习篇】从监督学习的懵懂起步至迁移学习的前沿瞭望</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/10149?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10149}" class="com-tag-v2">机器学习</a><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a><a href="/developer/tag/10790?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10790}" class="com-tag-v2">迁移学习</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/17440?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17440}" class="com-tag-v2">数据</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/11274339" track-click="{"objectType":"user","objectId":11274339}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/avatar/24339.png?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/11274339" track-click="{"objectType":"user","objectId":11274339}" target="_blank" class="author-info name">意疏</a><span class="author-info time"><time dateTime="2025-01-08 08:51:59" title="2025-01-08 08:51:59"> 2025-01-08<span class="com-v-box">2025-01-08 08:51:59</span></time></span></div></div></div><p class="com-article-panel-v2-des">机器学习（ML）是利用算法从数据中提取模式并进行预测或决策的技术。不同的学习范式适用于不同的任务和数据类型。本文将简要概述常见的机器学习范式，包括监督学习、无监...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>48</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2485372.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2482772" track-click="{"areaId":113001,"objectType":"article","objectId":2482772}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2482772}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">GPT理解的CV：基于Yolov5的半监督目标检测</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/17460?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17460}" class="com-tag-v2">算法</a><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a><a href="/developer/tag/13755?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":13755}" class="com-tag-v2">gpt</a><a href="/developer/tag/17353?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17353}" class="com-tag-v2">框架</a><a href="/developer/tag/17440?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17440}" class="com-tag-v2">数据</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/65d7a38323ecc9174aa1bfd95907d17d.jpg?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/1577869" track-click="{"objectType":"user","objectId":1577869}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://ask.qcloudimg.com/http-save/yehe-1577869/emq6640j7j.jpeg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/1577869" track-click="{"objectType":"user","objectId":1577869}" target="_blank" class="author-info name">计算机视觉研究院</a><span class="author-info time"><time dateTime="2024-12-30 15:11:10" title="2024-12-30 15:11:10"> 2024-12-30<span class="com-v-box">2024-12-30 15:11:10</span></time></span></div></div></div><p class="com-article-panel-v2-des">Epoch Adaptor是一种为密集探测器提供稳定高效的端到端SSOD训练计划的方法。伪标签分配器防止了在师生相互学习机制期间由大量低质量伪标签引起的可能干扰...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>121</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2482772.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2477802" track-click="{"areaId":113001,"objectType":"article","objectId":2477802}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2477802}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">机器学习总结</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/10332?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10332}" class="com-tag-v2">神经网络</a><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a><a href="/developer/tag/10722?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10722}" class="com-tag-v2">线性回归</a><a href="/developer/tag/17381?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17381}" class="com-tag-v2">模型</a><a href="/developer/tag/10149?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10149}" class="com-tag-v2">机器学习</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-11217379/2aa1205acb5f8745294f8fc7955303a7.png?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/11217379" track-click="{"objectType":"user","objectId":11217379}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/921bffda9eaacb11e05097f38ba8c27f.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/11217379" track-click="{"objectType":"user","objectId":11217379}" target="_blank" class="author-info name">zhangjiqun</a><span class="author-info time"><time dateTime="2024-12-17 09:12:13" title="2024-12-17 09:12:13"> 2024-12-17<span class="com-v-box">2024-12-17 09:12:13</span></time></span></div></div></div><p class="com-article-panel-v2-des">无监督学习方法主要提到的是聚类。随机选定几个样本，通过一定的算法不停迭代直至收敛或者达到停止条件，然后便将所有样本分成了几类。</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>98</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2477802.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2477045" track-click="{"areaId":113001,"objectType":"article","objectId":2477045}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2477045}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">机器学习:什么是分类/回归/聚类/降维/决策</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/17440?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17440}" class="com-tag-v2">数据</a><a href="/developer/tag/17460?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17460}" class="com-tag-v2">算法</a><a href="/developer/tag/10149?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10149}" class="com-tag-v2">机器学习</a><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a><a href="/developer/tag/17188?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17188}" class="com-tag-v2">变量</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-11217379/be1cdd55244693025c2a419a27d4fcf6.png?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/11217379" track-click="{"objectType":"user","objectId":11217379}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/921bffda9eaacb11e05097f38ba8c27f.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/11217379" track-click="{"objectType":"user","objectId":11217379}" target="_blank" class="author-info name">zhangjiqun</a><span class="author-info time"><time dateTime="2024-12-14 10:24:54" title="2024-12-14 10:24:54"> 2024-12-14<span class="com-v-box">2024-12-14 10:24:54</span></time></span></div></div></div><p class="com-article-panel-v2-des">从强化学习的基本原理能看出它与其他机器学习算法如监督学习和非监督学习的一些基本差别。在监督学习和非监督学习中，数据是静态的、不需要与环境进行交互，比如图像识别，...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>223</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2477045.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section><section class="com-article-panel-v2 higher"><a href="/developer/article/2476999" track-click="{"areaId":113001,"objectType":"article","objectId":2476999}" track-exposure="{"areaId":113001,"objectType":"article","objectId":2476999}" target="_blank" class="com-article-panel-v2-link"></a><div class="com-article-panel-v2-hd"><h3 class="com-article-panel-v2-title">梯度下降求极值，机器学习&深度学习</h3><nav class="com-tag-v2-list com-article-panel-v2-tags"><a href="/developer/tag/10539?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10539}" class="com-tag-v2">人工智能</a><a href="/developer/tag/10719?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10719}" class="com-tag-v2">监督学习</a><a href="/developer/tag/17290?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":17290}" class="com-tag-v2">函数</a><a href="/developer/tag/10149?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10149}" class="com-tag-v2">机器学习</a><a href="/developer/tag/10333?entry=article" track-click="{"areaId":113001,"objectType":"tag","objectId":10333}" class="com-tag-v2">深度学习</a></nav></div><div class="com-article-panel-v2-bd"><div class="com-article-panel-v2-object"><span class="com-article-panel-v2-img" style="background-image:url(https://developer.qcloudimg.com/http-save/yehe-11217379/9c945a3907d6fe54058f6d082a357633.png?imageView2/2/w/400/h/7000)"></span></div><div class="com-article-panel-v2-cnt"><div class="com-article-panel-v2-user-wrap"><div class="com-media com-user-infos"><a href="/developer/user/11217379" track-click="{"objectType":"user","objectId":11217379}" target="_blank" class="com-media-object"><span class="com-media-img" style="background-image:url(https://developer.qcloudimg.com/http-save/10011/921bffda9eaacb11e05097f38ba8c27f.jpg?imageView2/2/w/48/h/7000)"></span></a><div class="com-media-body"><a href="/developer/user/11217379" track-click="{"objectType":"user","objectId":11217379}" target="_blank" class="author-info name">zhangjiqun</a><span class="author-info time"><time dateTime="2024-12-14 09:46:02" title="2024-12-14 09:46:02"> 2024-12-14<span class="com-v-box">2024-12-14 09:46:02</span></time></span></div></div></div><p class="com-article-panel-v2-des">导数也叫导函数，或者微商，它是微积分中的重要基础概念，从物理学角度来看，导数是研究物体某一时刻的瞬时速度，比如你开车从家 8:00 出发到公司上班，9:00 到...</p><div class="com-operations com-article-panel-v2-opt"><span class="com-opt-link link-view"><i class="com-i-view"></i>80</span><span class="com-opt-link link-like"><i class="com-i-like"></i>1</span><span class="com-opt-link link-comment"><i class="com-i-dialog"></i>0</span><span><a href="javascript:;" class="com-opt-link link-share" hotrep="community.tag.tag_detail.activities.article.2476999.sharing"><i class="com-i-share"></i></a><ul class="com-share-options"></ul></span></div></div></div></section></div><div><div class="c-loading c-loading-tip"><div class="c-loading-inner"><div class="one"></div><div class="two"></div><div class="three"></div></div></div></div></div></div></div></div><div class="layout-side" track-click="" track-exposure=""><div class="com-2-section side"><header class="com-2-section-hd"><h2 class="com-2-section-title without-icon"><span><em>热门</em>专栏</span></h2></header><div class="com-2-section-bd"><div class="com-side-column-panels-wrap"><div class="com-side-column-panels-cnt"><ul track-click="{"areaId":113004}" track-exposure="{"areaId":113004}" class="com-side-column-panels"><li class="panel-cell"><a href="/developer/column/1014" trackClick="{"objectType":"column","objectId":1014}" class="com-media com-side-column-panel"><div class="com-media-object"><span class="com-2-avatar"><span class="com-2-avatar-inner" style="background-image:url(https://ask.qcloudimg.com/raw/yehe-b3360f6a89f75/eqohtul4uk.png?imageView2/2/w/76/h/7000)"></span></span></div><div class="com-media-body"><h3 class="com-side-column-panel-title">腾讯云开发者社区头条</h3><div class="com-side-column-panel-infos"><div class="com-datas"><span class="com-data">444 文章</span><span class="com-data">67.5K 订阅</span></div></div></div></a></li><li class="panel-cell"><a href="/developer/column/1023" trackClick="{"objectType":"column","objectId":1023}" class="com-media com-side-column-panel"><div class="com-media-object"><span class="com-2-avatar"><span class="com-2-avatar-inner" style="background-image:url(https://ask.qcloudimg.com/avatar/410635/l23egjzhlb.jpg?imageView2/2/w/76/h/7000)"></span></span></div><div class="com-media-body"><h3 class="com-side-column-panel-title">ArrayZoneYour的专栏</h3><div class="com-side-column-panel-infos"><div class="com-datas"><span class="com-data">17 文章</span><span class="com-data">45 订阅</span></div></div></div></a></li><li class="panel-cell"><a href="/developer/column/1108" trackClick="{"objectType":"column","objectId":1108}" class="com-media com-side-column-panel"><div class="com-media-object"><span class="com-2-avatar"><span class="com-2-avatar-inner" style="background-image:url(https://ask.qcloudimg.com/http-save/yehe-223114/gdt81byrq8.jpeg?imageView2/2/w/76/h/7000)"></span></span></div><div class="com-media-body"><h3 class="com-side-column-panel-title">进击的Coder</h3><div class="com-side-column-panel-infos"><div class="com-datas"><span class="com-data">559 文章</span><span class="com-data">201 订阅</span></div></div></div></a></li><li class="panel-cell"><a href="/developer/column/1172" trackClick="{"objectType":"column","objectId":1172}" class="com-media com-side-column-panel"><div class="com-media-object"><span class="com-2-avatar"><span class="com-2-avatar-inner" style="background-image:url(https://ask.qcloudimg.com/http-save/yehe-881770/11cbda56f3b4f304d8a26ffbf05b7066.png?imageView2/2/w/76/h/7000)"></span></span></div><div class="com-media-body"><h3 class="com-side-column-panel-title">腾讯云安全的专栏</h3><div class="com-side-column-panel-infos"><div class="com-datas"><span class="com-data">296 文章</span><span class="com-data">94 订阅</span></div></div></div></a></li></ul></div></div></div></div></div></div></div><div class="cdc-footer J-footer com-2-footer"><div class="cdc-footer__inner"><div class="cdc-footer__main"><div class="cdc-footer__website"><ul class="cdc-footer__website-group"><li class="cdc-footer__website-column"><div class="cdc-footer__website-box"><h3 class="cdc-footer__website-title">社区</h3><ul class="cdc-footer__website-list"><li class="cdc-footer__website-item"><a href="/developer/column">专栏文章</a></li><li class="cdc-footer__website-item"><a href="/developer/inventory">阅读清单</a></li><li class="cdc-footer__website-item"><a href="/developer/ask">互动问答</a></li><li class="cdc-footer__website-item"><a href="/developer/salon">技术沙龙</a></li><li class="cdc-footer__website-item"><a href="/developer/video">技术视频</a></li><li class="cdc-footer__website-item"><a href="/developer/teams">团队主页</a></li><li class="cdc-footer__website-item"><a href="/developer/timl">腾讯云TI平台</a></li></ul></div></li><li class="cdc-footer__website-column"><div class="cdc-footer__website-box"><h3 class="cdc-footer__website-title">活动</h3><ul class="cdc-footer__website-list"><li class="cdc-footer__website-item"><a href="/developer/support-plan">自媒体同步曝光计划</a></li><li class="cdc-footer__website-item"><a href="/developer/support-plan-invitation">邀请作者入驻</a></li><li class="cdc-footer__website-item"><a href="/developer/article/1535830">自荐上首页</a></li><li class="cdc-footer__website-item"><a href="/developer/competition">技术竞赛</a></li></ul></div></li><li class="cdc-footer__website-column"><div class="cdc-footer__website-box"><h3 class="cdc-footer__website-title">资源</h3><ul class="cdc-footer__website-list"><li class="cdc-footer__website-item"><a href="/developer/specials">技术周刊</a></li><li class="cdc-footer__website-item"><a href="/developer/tags">社区标签</a></li><li class="cdc-footer__website-item"><a href="/developer/devdocs">开发者手册</a></li><li class="cdc-footer__website-item"><a href="/lab?from=20064&from_column=20064">开发者实验室</a></li></ul></div></li><li class="cdc-footer__website-column"><div class="cdc-footer__website-box"><h3 class="cdc-footer__website-title">关于</h3><ul class="cdc-footer__website-list"><li class="cdc-footer__website-item"><a rel="nofollow" href="/developer/article/1006434">社区规范</a></li><li class="cdc-footer__website-item"><a rel="nofollow" href="/developer/article/1006435">免责声明</a></li><li class="cdc-footer__website-item"><a rel="nofollow" href="mailto:cloudcommunity@tencent.com">联系我们</a></li><li class="cdc-footer__website-item"><a rel="nofollow" href="/developer/friendlink">友情链接</a></li></ul></div></li></ul></div><div class="cdc-footer__qr"><h3 class="cdc-footer__qr-title">腾讯云开发者</h3><div class="cdc-footer__qr-object"><img class="cdc-footer__qr-image" src="https://qcloudimg.tencent-cloud.cn/raw/a8907230cd5be483497c7e90b061b861.png" alt="扫码关注腾讯云开发者"/></div><div class="cdc-footer__qr-infos"><p class="cdc-footer__qr-info"><span class="cdc-footer__qr-text">扫码关注腾讯云开发者</span></p><p class="cdc-footer__qr-info"><span class="cdc-footer__qr-text">领取腾讯云代金券</span></p></div></div></div><div class="cdc-footer__recommend"><div class="cdc-footer__recommend-rows"><div class="cdc-footer__recommend-cell"><h3 class="cdc-footer__recommend-title">热门产品</h3><div class="cdc-footer__recommend-wrap"><ul class="cdc-footer__recommend-list"><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="https://dnspod.cloud.tencent.com?from=20064&from_column=20064">域名注册</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/cvm?from=20064&from_column=20064">云服务器</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/tbaas?from=20064&from_column=20064">区块链服务</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/mq?from=20064&from_column=20064">消息队列</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/dsa?from=20064&from_column=20064">网络加速</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/tencentdb-catalog?from=20064&from_column=20064">云数据库</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/cns?from=20064&from_column=20064">域名解析</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/cos?from=20064&from_column=20064">云存储</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/css?from=20064&from_column=20064">视频直播</a></li></ul></div></div><div class="cdc-footer__recommend-cell"><h3 class="cdc-footer__recommend-title">热门推荐</h3><div class="cdc-footer__recommend-wrap"><ul class="cdc-footer__recommend-list"><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/facerecognition?from=20064&from_column=20064">人脸识别</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/tm?from=20064&from_column=20064">腾讯会议</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/act/pro/enterprise2019?from=20064&from_column=20064">企业云</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/cdn-scd?from=20064&from_column=20064">CDN加速</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/trtc?from=20064&from_column=20064">视频通话</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/tiia?from=20064&from_column=20064">图像分析</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/cdb?from=20064&from_column=20064">MySQL 数据库</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/symantecssl?from=20064&from_column=20064">SSL 证书</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/asr?from=20064&from_column=20064">语音识别</a></li></ul></div></div><div class="cdc-footer__recommend-cell"><h3 class="cdc-footer__recommend-title">更多推荐</h3><div class="cdc-footer__recommend-wrap"><ul class="cdc-footer__recommend-list"><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/solution/data_protection?from=20064&from_column=20064">数据安全</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/clb?from=20064&from_column=20064">负载均衡</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/sms?from=20064&from_column=20064">短信</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/ocr?from=20064&from_column=20064">文字识别</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/vod?from=20064&from_column=20064">云点播</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="https://tm.cloud.tencent.com?from=20064&from_column=20064">商标注册</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/solution/la?from=20064&from_column=20064">小程序开发</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/cat?from=20064&from_column=20064">网站监控</a></li><li class="cdc-footer__recommend-item"><a class="com-2-footer-recommend-link" href="/product/cdm?from=20064&from_column=20064">数据迁移</a></li></ul></div></div></div></div><div class="cdc-footer__copyright"><div class="cdc-footer__copyright-text"><p>Copyright © 2013 - <!-- -->2025<!-- --> Tencent Cloud. All Rights Reserved. 腾讯云 版权所有<!-- --> </p><p>深圳市腾讯计算机系统有限公司 ICP备案/许可证号：<a href="https://beian.miit.gov.cn/#/Integrated/index" target="_blank">粤B2-20090059<!-- --> </a><a href="https://www.beian.gov.cn/portal/index.do" target="_blank">深公网安备号 44030502008569</a></p><p>腾讯云计算（北京）有限责任公司 京ICP证150476号 | <!-- --> <a href="https://beian.miit.gov.cn/#/Integrated/index" target="_blank">京ICP备11018762号</a> | <!-- --> <a href="https://www.beian.gov.cn/portal/index.do" target="_blank">京公网安备号11010802020287</a></p></div></div></div></div></div><div class="com-widget-global"><div style="position:relative;z-index:8088"><div class="com-widget-global2"><div class="com-widget-global2__btn code"><div class="com-widget-global2__btn-tag">领券</div></div><div class="com-widget-global2__btn top" style="visibility:hidden"></div></div></div></div><div id="dialog-root"></div><div id="rno-dialog-root" class="rno-modal-wrap"></div></div><script>window.isServerContext = false; window.isClientContext = true;</script><script>window.$serverTime = 1740480702682; window.$clientTime = 1740480702682;</script><script class="">window.$ua = {"browser":{"name":"IE","version":"7.0","major":"7"},"cpu":{},"device":{},"engine":{},"os":{"name":"Windows","version":"Vista"}};</script><script src="//cloudcache.tencent-cloud.com/qcloud/developer/scripts/release/libs/dom4/1.8.3/dom4.js"></script><script src="https://cloudcache.tencent-cloud.com/qcloud/main/scripts/release/common/vendors/babel/polyfill.6.26.min.js"></script><script src="https://cloudcache.tencent-cloud.com/qcloud/main/scripts/release/common/vendors/react/react.16.8.6.min.js"></script><script src="https://cloudcache.tencent-cloud.com/qcloud/main/scripts/release/common/vendors/react/react-dom.16.8.6.min.js"></script><script src="https://cloudcache.tencent-cloud.com/qcloud/main/scripts/release/common/vendors/jquery-3.2.1.min.js"></script><script src="//cloudcache.tencent-cloud.com/qcloud/developer/scripts/release/base.225e98f95c.js?max_age=31536000" crossorigin="anonymous"></script><script src="//cloudcache.tencent-cloud.com/qcloud/draft-master/dist/draft-master-v2.0.165.d4s2ddo9sb.js?max_age=31536000"></script><script src="https://cloud.tencent.com/qccomponent/login/api.js"></script><script src="//cloudcache.tencent-cloud.com/qcloud/main/scripts/release/common/deps/wechatJsSdk.js?version=1_0_1&max_age=31536000"></script><script src="//cloudcache.tencent-cloud.com/qcloud/developer/scripts/release/common.4ebc077d54.js?max_age=31536000" crossorigin="anonymous"></script><script src="https://web.sdk.qcloud.com/player/tcplayer/release/v4.7.2/tcplayer.v4.7.2.min.js"></script><script src="//dscache.tencent-cloud.cn/ecache/qcstat/qcloud/qcloudStatApi.js"></script><script src="https://qccommunity.qcloudimg.com/common/exposure-plugin-4.1.15.min.js"></script><script src="https://qccommunity.qcloudimg.com/community-track/qcloud-community-track.min.js"></script><script src="https://dscache.tencent-cloud.com/sdk/dianshi-sdk/loader/umd/dianshi-sdk-loader.v0.0.18.js"></script><script src="//cloudcache.tencent-cloud.com/qcloud/developer/scripts/release/tag/tag-detail.16dc4ab4f9.js?max_age=31536000" crossorigin="anonymous"></script><script class=""> window.$render({"tagInfo":{"id":10719,"name":"监督学习","icon":"","defaultIcon":"//cloudcache.tencent-cloud.com/open_proj/proj_qcloud_v2/gateway/q-and-a/css/img/tags/tag_comm.svg","shareIcon":"https://cloudcache.tencent-cloud.com/open_proj/proj_qcloud_v2/gateway/q-and-a/css/img/tags/share_comm.png","initial":"J","desc":"监督式学习，是一个机器学习中的方法，可以由训练资料中学到或建立一个模式，并依此模式推测新的实例。","followCount":3,"questionCount":10,"answerCount":55,"unanswerCount":2,"articleCount":1929,"devdocCount":0,"vlogCount":0,"boundProductId":0,"stick":{"articleIds":[],"askIds":[],"vlogIds":[]},"createTime":"2018-09-06 18:31:33"},"activeRelatedEntry":"article","timelineData":{"ask":{"fetchStatus":"none","done":false,"nextPageNumber":1,"pageSize":20,"total":0,"list":[]},"article":{"fetchStatus":"loaded","done":false,"nextPageNumber":2,"pageSize":20,"total":1929,"list":[{"id":2497901,"articleId":2497901,"title":"苹果也在蒸馏大模型，给出了蒸馏Scaling Laws","content":"","plain":"","brief":"","summary":"该结果表明，当两个学习过程都有足够的数据或计算时，蒸馏不能产生比监督学习更低的模型交叉熵。但是，如果以下两个条件都成立，则蒸馏比监督学习更有效：","abstract":"该结果表明，当两个学习过程都有足够的数据或计算时，蒸馏不能产生比监督学习更低的模型交叉熵。但是，如果以下两个条件都成立，则蒸馏比监督学习更有效：","posterSummary":"","description":"","picture":"https://developer.qcloudimg.com/http-save/10011/455fb5110891e0133dc1784094846036.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/10011/455fb5110891e0133dc1784094846036.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":1754229,"columnId":2713,"columnIds":[],"writeTime":1739977262,"updateTime":1739977262,"viewCount":73,"likeCount":0,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://ask.qcloudimg.com/avatar/1754229/32embxnqwf.jpg","company":"","introduce":"专业的人工智能媒体和产业服务平台","isProfessionVerified":0,"nickname":"机器之心","title":"全球人工智能信息服务","uid":1754229,"id":1754229,"name":"机器之心","avatar":"https://ask.qcloudimg.com/avatar/1754229/32embxnqwf.jpg"},"tags":[{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"},{"tagId":15852,"tagName":"scaling","id":15852,"name":"scaling"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":17394,"tagName":"苹果","id":17394,"name":"苹果"},{"tagId":17440,"tagName":"数据","id":17440,"name":"数据"}]},{"id":2497052,"articleId":2497052,"title":"怎么知道效果提升了？7个用于改进RAG系统的检索指标","content":"","plain":"","brief":"","summary":"准确率通常定义为正确预测的比例（包括真正例和真负例）与总案例数之比。如果你熟悉监督学习中的分类问题，可能已经对这个指标有所了解。在检索和RAG的背景下，它的计算...","abstract":"准确率通常定义为正确预测的比例（包括真正例和真负例）与总案例数之比。如果你熟悉监督学习中的分类问题，可能已经对这个指标有所了解。在检索和RAG的背景下，它的计算...","posterSummary":"准确率通常定义为正确预测的比例（包括真正例和真负例）与总案例数之比。如果你熟悉监督学习中的分类问题，可能已经对这个指标有所了解。在检索和RAG的背景下，它的计算方式如下：","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-100000/8e0b86e9a455f17074ee8c7d4424643e.png","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-100000/8e0b86e9a455f17074ee8c7d4424643e.png","sourceType":99,"sourceDetail":{},"channelType":2,"channelDetail":{},"authorId":1293914,"columnId":2353,"columnIds":[],"writeTime":1739789262,"updateTime":1739789262,"viewCount":127,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/6af473c5f2793c53e00484d0b037754e.jpg","company":"ICT","introduce":"think triple，act double","isProfessionVerified":0,"nickname":"致Great","title":"自然语言处理实习","uid":1293914,"id":1293914,"name":"致Great","avatar":"https://developer.qcloudimg.com/http-save/10011/6af473c5f2793c53e00484d0b037754e.jpg"},"tags":[{"tagId":17506,"tagName":"系统","id":17506,"name":"系统"},{"tagId":17525,"tagName":"性能","id":17525,"name":"性能"},{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"},{"tagId":17390,"tagName":"排序","id":17390,"name":"排序"},{"tagId":17440,"tagName":"数据","id":17440,"name":"数据"}]},{"id":2495099,"articleId":2495099,"title":"AI应用实战课学习总结（1）必备AI基础理论","content":"","plain":"","brief":"","summary":"由于公司的愿景逐渐调整为ONE Tech Company，公司的IT战略也逐渐地朝着Data & AI Driven发展，因此近半年来我一直在学习大模型相关的东...","abstract":"由于公司的愿景逐渐调整为ONE Tech Company，公司的IT战略也逐渐地朝着Data & AI Driven发展，因此近半年来我一直在学习大模型相关的东...","posterSummary":"由于公司的愿景逐渐调整为ONE Tech Company，公司的IT战略也逐渐地朝着Data & AI Driven发展，因此近半年来我一直在学习大模型相关的东西，从ChatGPT到Agent都有所涉及。","description":"","picture":"https://developer.qcloudimg.com/http-save/10011/bbe5b29842631c99955c097357efe836.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/10011/bbe5b29842631c99955c097357efe836.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":7499234,"columnId":89717,"columnIds":[],"writeTime":1739188029,"updateTime":1739188029,"viewCount":108,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://ask.qcloudimg.com/http-save/yehe-7499234/c96c64adf4850c3af5eb82a172828dcb.jpeg","company":"","introduce":"微软 MVP，公众号：DotNet NB，CloudNative NB","isProfessionVerified":0,"nickname":"郑子铭","title":"后端开发工程师","uid":7499234,"id":7499234,"name":"郑子铭","avatar":"https://ask.qcloudimg.com/http-save/yehe-7499234/c96c64adf4850c3af5eb82a172828dcb.jpeg"},"tags":[{"tagId":10333,"tagName":"深度学习","id":10333,"name":"深度学习"},{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":17440,"tagName":"数据","id":17440,"name":"数据"},{"tagId":10149,"tagName":"机器学习","id":10149,"name":"机器学习"}]},{"id":2492741,"articleId":2492741,"title":"首个公开发表的SAR图像目标识别基础模型！国防科大刘永祥&刘丽教授团队提出SARATR-X 1.0","content":"","plain":"","brief":"","summary":"合成孔径雷达（Synthetic Aperture Radar, SAR）作为一种基于电磁波的主动探测技术，具有全天时、全天候的对地观测能力，已发展成为一种不可...","abstract":"合成孔径雷达（Synthetic Aperture Radar, SAR）作为一种基于电磁波的主动探测技术，具有全天时、全天候的对地观测能力，已发展成为一种不可...","posterSummary":"合成孔径雷达（Synthetic Aperture Radar, SAR）作为一种基于电磁波的主动探测技术，具有全天时、全天候的对地观测能力，已发展成为一种不可或缺的对地观测工具，在军民很多领域均有着重要的应用。","description":"","picture":"https://developer.qcloudimg.com/http-save/10011/3e5a6e6a327b059b22a00557fed21bf3.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/10011/3e5a6e6a327b059b22a00557fed21bf3.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":1754229,"columnId":2713,"columnIds":[],"writeTime":1738565566,"updateTime":1738565566,"viewCount":210,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://ask.qcloudimg.com/avatar/1754229/32embxnqwf.jpg","company":"","introduce":"专业的人工智能媒体和产业服务平台","isProfessionVerified":0,"nickname":"机器之心","title":"全球人工智能信息服务","uid":1754229,"id":1754229,"name":"机器之心","avatar":"https://ask.qcloudimg.com/avatar/1754229/32embxnqwf.jpg"},"tags":[{"tagId":10667,"tagName":"开源","id":10667,"name":"开源"},{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"},{"tagId":17302,"tagName":"基础","id":17302,"name":"基础"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":17440,"tagName":"数据","id":17440,"name":"数据"}]},{"id":2491711,"articleId":2491711,"title":"AI Vision 2024：CVPR 引爆科技核爆，解锁计算机视觉未来无限可能！","content":"","plain":"","brief":"","summary":"随着人工智能（AI）的飞速发展，计算机视觉（CV）已经成为支撑多种AI应用的重要基础。从自动驾驶汽车、面部识别系统到精准医疗影像分析，计算机视觉的技术正在极大地...","abstract":"随着人工智能（AI）的飞速发展，计算机视觉（CV）已经成为支撑多种AI应用的重要基础。从自动驾驶汽车、面部识别系统到精准医疗影像分析，计算机视觉的技术正在极大地...","posterSummary":"随着人工智能（AI）的飞速发展，计算机视觉（CV）已经成为支撑多种AI应用的重要基础。从自动驾驶汽车、面部识别系统到精准医疗影像分析，计算机视觉的技术正在极大地改变社会各行各业。CVPR（计算机视觉与模式识别会议）一直是全球计算机视觉领域最为权威的学术会议之一。每年，成千上万的研究人员和工程师通过CVPR展示最新的技术成果和创新思路。2024年的CVPR，带来了令人瞩目的技术突破，标志着计算机视觉...","description":"","picture":"","coverImageUrl":"","sourceType":99,"sourceDetail":{},"channelType":2,"channelDetail":{},"authorId":11458826,"columnId":104772,"columnIds":[],"writeTime":1737806373,"updateTime":1737806373,"viewCount":93,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/avatar/8826.png","company":"","introduce":"","isProfessionVerified":0,"nickname":"用户11458826","title":"","uid":11458826,"id":11458826,"name":"用户11458826","avatar":"https://developer.qcloudimg.com/avatar/8826.png"},"tags":[{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"},{"tagId":17310,"tagName":"计算机视觉","id":17310,"name":"计算机视觉"},{"tagId":17347,"tagName":"科技","id":17347,"name":"科技"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":17440,"tagName":"数据","id":17440,"name":"数据"}]},{"id":2490784,"articleId":2490784,"title":"【机器学习-监督学习】朴素贝叶斯","content":"","plain":"","brief":"","summary":" 贝叶斯分类是一类分类算法的总称，这类算法均以贝叶斯定理为基础，所以统称为贝叶斯分类。朴素贝叶斯是一种贝叶斯分类算法，在许多场合可以与决策树和神经网络分类算法...","abstract":" 贝叶斯分类是一类分类算法的总称，这类算法均以贝叶斯定理为基础，所以统称为贝叶斯分类。朴素贝叶斯是一种贝叶斯分类算法，在许多场合可以与决策树和神经网络分类算法...","posterSummary":" 贝叶斯分类是一类分类算法的总称，这类算法均以贝叶斯定理为基础，所以统称为贝叶斯分类。朴素贝叶斯是一种贝叶斯分类算法，在许多场合可以与决策树和神经网络分类算法相媲美。图1展示了贝叶斯原理、贝叶斯分类和朴素贝叶斯三者之间的关系。","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-100000/c5a078734ef07f3b5710ec4e0a608016.png","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-100000/c5a078734ef07f3b5710ec4e0a608016.png","sourceType":99,"sourceDetail":{},"channelType":2,"channelDetail":{},"authorId":11457362,"columnId":104758,"columnIds":[],"writeTime":1737560439,"updateTime":1737560439,"viewCount":102,"likeCount":0,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/85f1d5aca973f3d501211269bdba7e3c.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"Francek Chen","title":"","uid":11457362,"id":11457362,"name":"Francek Chen","avatar":"https://developer.qcloudimg.com/http-save/10011/85f1d5aca973f3d501211269bdba7e3c.jpg"},"tags":[{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":17440,"tagName":"数据","id":17440,"name":"数据"},{"tagId":10149,"tagName":"机器学习","id":10149,"name":"机器学习"},{"tagId":10490,"tagName":"短信","id":10490,"name":"短信"},{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"}]},{"id":2490783,"articleId":2490783,"title":"【机器学习-监督学习】集成学习与梯度提升决策树","content":"","plain":"","brief":"","summary":" 本文将会首先介绍集成学习的思路以及一些常用的集成学习方法，然后介绍梯度提升决策树模型。在前面的文章中，我们讲解了许多不同的机器学习算法，每个算法都有其独特的...","abstract":" 本文将会首先介绍集成学习的思路以及一些常用的集成学习方法，然后介绍梯度提升决策树模型。在前面的文章中，我们讲解了许多不同的机器学习算法，每个算法都有其独特的...","posterSummary":" 本文将会首先介绍集成学习的思路以及一些常用的集成学习方法，然后介绍梯度提升决策树模型。在前面的文章中，我们讲解了许多不同的机器学习算法，每个算法都有其独特的优缺点。同时，对于同一个任务，往往有多种算法可以将其解决。例如我们要将平面上的一些点分类，假设算法一和算法二的正确率是75%，算法三是50%。3种算法都已经通过调参达到了其最优表现，已经无法再进一步了。那么，我们是否能通过组合这些算法，得到...","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-11457362/d770866cdf04d54a6c1e60e4629f12b2.png","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-11457362/d770866cdf04d54a6c1e60e4629f12b2.png","sourceType":99,"sourceDetail":{},"channelType":2,"channelDetail":{},"authorId":11457362,"columnId":104758,"columnIds":[],"writeTime":1737560381,"updateTime":1737560381,"viewCount":123,"likeCount":0,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/85f1d5aca973f3d501211269bdba7e3c.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"Francek Chen","title":"","uid":11457362,"id":11457362,"name":"Francek Chen","avatar":"https://developer.qcloudimg.com/http-save/10011/85f1d5aca973f3d501211269bdba7e3c.jpg"},"tags":[{"tagId":17460,"tagName":"算法","id":17460,"name":"算法"},{"tagId":10149,"tagName":"机器学习","id":10149,"name":"机器学习"},{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"},{"tagId":10721,"tagName":"决策树","id":10721,"name":"决策树"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"}]},{"id":2490782,"articleId":2490782,"title":"【机器学习-监督学习】决策树","content":"","plain":"","brief":"","summary":" 本文开始，我们将介绍机器学习中与神经网络并行的另一大类模型——决策树（decision tree）模型及其变种。决策树模型是非参数化模型。决策树模型简称树模...","abstract":" 本文开始，我们将介绍机器学习中与神经网络并行的另一大类模型——决策树（decision tree）模型及其变种。决策树模型是非参数化模型。决策树模型简称树模...","posterSummary":" 本文开始，我们将介绍机器学习中与神经网络并行的另一大类模型——决策树（decision tree）模型及其变种。决策树模型是非参数化模型。决策树模型简称树模型，顾名思义，它采用了和树类似的结构。图1展示了现实中的树与计算机中的树的异同。现实中的树是根在下、从下向上生长的，计算机中的树却是根在上、从上向下生长的。但是，两者都有根、枝干的分叉与叶子。在计算机的树中，最上面的节点称为根节点，最下面没...","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-11457362/c8272686ac7a4e44c5c221175404dae8.png","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-11457362/c8272686ac7a4e44c5c221175404dae8.png","sourceType":99,"sourceDetail":{},"channelType":2,"channelDetail":{},"authorId":11457362,"columnId":104758,"columnIds":[],"writeTime":1737559852,"updateTime":1737559852,"viewCount":81,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/85f1d5aca973f3d501211269bdba7e3c.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"Francek Chen","title":"","uid":11457362,"id":11457362,"name":"Francek Chen","avatar":"https://developer.qcloudimg.com/http-save/10011/85f1d5aca973f3d501211269bdba7e3c.jpg"},"tags":[{"tagId":10149,"tagName":"机器学习","id":10149,"name":"机器学习"},{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"},{"tagId":10721,"tagName":"决策树","id":10721,"name":"决策树"},{"tagId":17440,"tagName":"数据","id":17440,"name":"数据"},{"tagId":17460,"tagName":"算法","id":17460,"name":"算法"}]},{"id":2490779,"articleId":2490779,"title":"【机器学习-监督学习】神经网络与多层感知机","content":"","plain":"","brief":"","summary":" 本文将会介绍机器学习中最重要的内容之一——神经网络（neural network，NN），它是深度学习的基础。神经网络的名称来源于生物中的神经元。自有计算机...","abstract":" 本文将会介绍机器学习中最重要的内容之一——神经网络（neural network，NN），它是深度学习的基础。神经网络的名称来源于生物中的神经元。自有计算机...","posterSummary":" 本文将会介绍机器学习中最重要的内容之一——神经网络（neural network，NN），它是深度学习的基础。神经网络的名称来源于生物中的神经元。自有计算机以来，人们就希望能让计算机具有和人类一样的智能，因此，许多研究者将目光放到了人类的大脑结构上。作为生物神经系统的基本单元，神经元在形成智能的过程中起到了关键作用。神经元的结构并不复杂，简单来说，神经元由树突、轴突和细胞体构成。图1是神经元的...","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-100000/a7dacf9aa3e7171f52746b9e2c6381ff.png","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-100000/a7dacf9aa3e7171f52746b9e2c6381ff.png","sourceType":99,"sourceDetail":{},"channelType":2,"channelDetail":{},"authorId":11457362,"columnId":104758,"columnIds":[],"writeTime":1737559460,"updateTime":1737559460,"viewCount":137,"likeCount":0,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/85f1d5aca973f3d501211269bdba7e3c.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"Francek Chen","title":"","uid":11457362,"id":11457362,"name":"Francek Chen","avatar":"https://developer.qcloudimg.com/http-save/10011/85f1d5aca973f3d501211269bdba7e3c.jpg"},"tags":[{"tagId":10149,"tagName":"机器学习","id":10149,"name":"机器学习"},{"tagId":10332,"tagName":"神经网络","id":10332,"name":"神经网络"},{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"},{"tagId":17290,"tagName":"函数","id":17290,"name":"函数"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"}]},{"id":2490777,"articleId":2490777,"title":"【机器学习-监督学习】双线性模型","content":"","plain":"","brief":"","summary":" 从本文开始，我们介绍参数化模型中的非线性模型。在前几篇文章中，我们介绍了线性回归与逻辑斯谛回归模型。这两个模型都有一个共同的特征：包含线性预测因子","abstract":" 从本文开始，我们介绍参数化模型中的非线性模型。在前几篇文章中，我们介绍了线性回归与逻辑斯谛回归模型。这两个模型都有一个共同的特征：包含线性预测因子","posterSummary":"","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-11457362/240b595d4c80e69673e4490b2a24fb60.png","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-11457362/240b595d4c80e69673e4490b2a24fb60.png","sourceType":99,"sourceDetail":{},"channelType":2,"channelDetail":{},"authorId":11457362,"columnId":104758,"columnIds":[],"writeTime":1737559138,"updateTime":1737559138,"viewCount":76,"likeCount":0,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/85f1d5aca973f3d501211269bdba7e3c.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"Francek Chen","title":"","uid":11457362,"id":11457362,"name":"Francek Chen","avatar":"https://developer.qcloudimg.com/http-save/10011/85f1d5aca973f3d501211269bdba7e3c.jpg"},"tags":[{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"},{"tagId":17290,"tagName":"函数","id":17290,"name":"函数"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":17440,"tagName":"数据","id":17440,"name":"数据"},{"tagId":10149,"tagName":"机器学习","id":10149,"name":"机器学习"}]},{"id":2490776,"articleId":2490776,"title":"【机器学习-监督学习】逻辑斯谛回归","content":"","plain":"","brief":"","summary":" 在介绍了机器学习中相关的基本概念和技巧后，本章我们继续讲解参数化模型中的线性模型。有了前文的基础，我们可以先来对KNN算法和线性回归进行比较，进一步回答“什...","abstract":" 在介绍了机器学习中相关的基本概念和技巧后，本章我们继续讲解参数化模型中的线性模型。有了前文的基础，我们可以先来对KNN算法和线性回归进行比较，进一步回答“什...","posterSummary":" 在介绍了机器学习中相关的基本概念和技巧后，本章我们继续讲解参数化模型中的线性模型。有了前文的基础，我们可以先来对KNN算法和线性回归进行比较，进一步回答“什么是参数化模型”这一问题。对于机器学习算法来说，其目标通常可以抽象为得到某个从输入空间到输出空间的映射 ","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-11457362/ee73d8c0e1bd433cea97640d471f19c4.png","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-11457362/ee73d8c0e1bd433cea97640d471f19c4.png","sourceType":99,"sourceDetail":{},"channelType":2,"channelDetail":{},"authorId":11457362,"columnId":104758,"columnIds":[],"writeTime":1737559031,"updateTime":1737559031,"viewCount":125,"likeCount":0,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/85f1d5aca973f3d501211269bdba7e3c.jpg","company":"","introduce":"","isProfessionVerified":0,"nickname":"Francek Chen","title":"","uid":11457362,"id":11457362,"name":"Francek Chen","avatar":"https://developer.qcloudimg.com/http-save/10011/85f1d5aca973f3d501211269bdba7e3c.jpg"},"tags":[{"tagId":10149,"tagName":"机器学习","id":10149,"name":"机器学习"},{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"},{"tagId":17290,"tagName":"函数","id":17290,"name":"函数"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":17440,"tagName":"数据","id":17440,"name":"数据"}]},{"id":2490407,"articleId":2490407,"title":"首个公开发表的SAR图像目标识别基础模型！国防科大刘永祥&刘丽教授团队提出SARATR-X 1.0","content":"","plain":"","brief":"","summary":"合成孔径雷达（Synthetic Aperture Radar, SAR）作为一种基于电磁波的主动探测技术，具有全天时、全天候的对地观测能力，已发展成为一种不可...","abstract":"合成孔径雷达（Synthetic Aperture Radar, SAR）作为一种基于电磁波的主动探测技术，具有全天时、全天候的对地观测能力，已发展成为一种不可...","posterSummary":"合成孔径雷达（Synthetic Aperture Radar, SAR）作为一种基于电磁波的主动探测技术，具有全天时、全天候的对地观测能力，已发展成为一种不可或缺的对地观测工具，在军民很多领域均有着重要的应用。","description":"","picture":"https://developer.qcloudimg.com/http-save/10011/a1d54a2dc08e751d32f2960934241461.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/10011/a1d54a2dc08e751d32f2960934241461.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":1577869,"columnId":2331,"columnIds":[],"writeTime":1737520886,"updateTime":1737520886,"viewCount":99,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://ask.qcloudimg.com/http-save/yehe-1577869/emq6640j7j.jpeg","company":"","introduce":"公众号：计算机视觉研究院","isProfessionVerified":0,"nickname":"计算机视觉研究院","title":"","uid":1577869,"id":1577869,"name":"计算机视觉研究院","avatar":"https://ask.qcloudimg.com/http-save/yehe-1577869/emq6640j7j.jpeg"},"tags":[{"tagId":10667,"tagName":"开源","id":10667,"name":"开源"},{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"},{"tagId":17302,"tagName":"基础","id":17302,"name":"基础"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":17440,"tagName":"数据","id":17440,"name":"数据"}]},{"id":2488061,"articleId":2488061,"title":"一文详尽之Embedding（向量表示）！","content":"","plain":"","brief":"","summary":"文本是一类非常重要的非结构化数据，如何表示文本数据一直是机器学习领域的一个重点研究方向。文本向量就是深度学习时代产生的一种文本表示的方法。","abstract":"文本是一类非常重要的非结构化数据，如何表示文本数据一直是机器学习领域的一个重点研究方向。文本向量就是深度学习时代产生的一种文本表示的方法。","posterSummary":"","description":"","picture":"https://developer.qcloudimg.com/http-save/10011/bd9132720f8d6a97645c2ca6ed4ca3cc.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/10011/bd9132720f8d6a97645c2ca6ed4ca3cc.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":4303953,"columnId":78434,"columnIds":[],"writeTime":1737288082,"updateTime":1737288082,"viewCount":274,"likeCount":0,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://ask.qcloudimg.com/http-save/yehe-4303953/1akvz8h16e.jpeg","company":"","introduce":"","isProfessionVerified":0,"nickname":"Datawhale","title":"","uid":4303953,"id":4303953,"name":"Datawhale","avatar":"https://ask.qcloudimg.com/http-save/yehe-4303953/1akvz8h16e.jpeg"},"tags":[{"tagId":17440,"tagName":"数据","id":17440,"name":"数据"},{"tagId":17554,"tagName":"优化","id":17554,"name":"优化"},{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"},{"tagId":13234,"tagName":"embedding","id":13234,"name":"embedding"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"}]},{"id":2486288,"articleId":2486288,"title":"不需要标注了？看自监督学习框架如何助力目标检测","content":"","plain":"","brief":"","summary":"论文链接：https://arxiv.org/pdf/2104.08683.pdf","abstract":"论文链接：https://arxiv.org/pdf/2104.08683.pdf","posterSummary":"","description":"","picture":"https://developer.qcloudimg.com/http-save/10011/f9d7ede4a46cf75c51675d5d5997a4cf.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/10011/f9d7ede4a46cf75c51675d5d5997a4cf.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":1577869,"columnId":2331,"columnIds":[],"writeTime":1736658045,"updateTime":1736658045,"viewCount":120,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://ask.qcloudimg.com/http-save/yehe-1577869/emq6640j7j.jpeg","company":"","introduce":"公众号：计算机视觉研究院","isProfessionVerified":0,"nickname":"计算机视觉研究院","title":"","uid":1577869,"id":1577869,"name":"计算机视觉研究院","avatar":"https://ask.qcloudimg.com/http-save/yehe-1577869/emq6640j7j.jpeg"},"tags":[{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"},{"tagId":17353,"tagName":"框架","id":17353,"name":"框架"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":17525,"tagName":"性能","id":17525,"name":"性能"},{"tagId":10147,"tagName":"自动驾驶","id":10147,"name":"自动驾驶"}]},{"id":2485824,"articleId":2485824,"title":"时序论文35｜LPTM：用于跨领域时序任务预训练模型（引入动态切分）","content":"","plain":"","brief":"","summary":"首先要知道文中说的SSL loss，SSL 是 Self - Supervised Learning（自监督学习）的缩写，SSL loss 即自监督学习损失。用...","abstract":"首先要知道文中说的SSL loss，SSL 是 Self - Supervised Learning（自监督学习）的缩写，SSL loss 即自监督学习损失。用...","posterSummary":"首先要知道文中说的SSL loss，SSL 是 Self - Supervised Learning（自监督学习）的缩写，SSL loss 即自监督学习损失。用于评估自监督学习任务的性能。那么很自然的，在预训练阶段，可以通过寻找让 SSL loss 尽可能低的分割策略，帮助模型更好地捕捉时间序列内在结构和模式。","description":"","picture":"https://developer.qcloudimg.com/http-save/10011/2d98e120e1934df28543ee6cc5f02332.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/10011/2d98e120e1934df28543ee6cc5f02332.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":4434621,"columnId":103774,"columnIds":[],"writeTime":1736425959,"updateTime":1736425959,"viewCount":137,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/d475988d13f7edf01d8a40a916381bb0.jpg","company":"","introduce":"公众号【科学最top】，追踪时间序列领域高水平研究和新突破，解读最新时序论文","isProfessionVerified":0,"nickname":"科学最Top","title":"","uid":4434621,"id":4434621,"name":"科学最Top","avatar":"https://developer.qcloudimg.com/http-save/10011/d475988d13f7edf01d8a40a916381bb0.jpg"},"tags":[{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":17440,"tagName":"数据","id":17440,"name":"数据"},{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"},{"tagId":17303,"tagName":"集合","id":17303,"name":"集合"},{"tagId":17373,"tagName":"论文","id":17373,"name":"论文"}]},{"id":2485372,"articleId":2485372,"title":"【机器学习篇】从监督学习的懵懂起步至迁移学习的前沿瞭望","content":"","plain":"","brief":"","summary":"机器学习（ML）是利用算法从数据中提取模式并进行预测或决策的技术。不同的学习范式适用于不同的任务和数据类型。本文将简要概述常见的机器学习范式，包括监督学习、无监...","abstract":"机器学习（ML）是利用算法从数据中提取模式并进行预测或决策的技术。不同的学习范式适用于不同的任务和数据类型。本文将简要概述常见的机器学习范式，包括监督学习、无监...","posterSummary":"机器学习（ML）是利用算法从数据中提取模式并进行预测或决策的技术。不同的学习范式适用于不同的任务和数据类型。本文将简要概述常见的机器学习范式，包括监督学习、无监督学习、强化学习、半监督学习、自监督学习及迁移学习","description":"","picture":"","coverImageUrl":"","sourceType":99,"sourceDetail":{},"channelType":2,"channelDetail":{},"authorId":11274339,"columnId":104282,"columnIds":[],"writeTime":1736297519,"updateTime":1736297519,"viewCount":48,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/avatar/24339.png","company":"","introduce":"","isProfessionVerified":0,"nickname":"意疏","title":"","uid":11274339,"id":11274339,"name":"意疏","avatar":"https://developer.qcloudimg.com/avatar/24339.png"},"tags":[{"tagId":10149,"tagName":"机器学习","id":10149,"name":"机器学习"},{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"},{"tagId":10790,"tagName":"迁移学习","id":10790,"name":"迁移学习"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":17440,"tagName":"数据","id":17440,"name":"数据"}]},{"id":2482772,"articleId":2482772,"title":"GPT理解的CV：基于Yolov5的半监督目标检测","content":"","plain":"","brief":"","summary":"Epoch Adaptor是一种为密集探测器提供稳定高效的端到端SSOD训练计划的方法。伪标签分配器防止了在师生相互学习机制期间由大量低质量伪标签引起的可能干扰...","abstract":"Epoch Adaptor是一种为密集探测器提供稳定高效的端到端SSOD训练计划的方法。伪标签分配器防止了在师生相互学习机制期间由大量低质量伪标签引起的可能干扰...","posterSummary":"Epoch Adaptor是一种为密集探测器提供稳定高效的端到端SSOD训练计划的方法。伪标签分配器防止了在师生相互学习机制期间由大量低质量伪标签引起的可能干扰密集检测器的偏差的发生，并且Epoch适配器利用域和分布自适应来允许密集检测器学习全局分布的一致特征，使得训练与标记数据的比例无关。我们的实验表明，高效教师框架在VOC、COCO标准和COCO附加方面取得了最先进的结果，使用的FLOP比以前...","description":"","picture":"https://developer.qcloudimg.com/http-save/10011/65d7a38323ecc9174aa1bfd95907d17d.jpg","coverImageUrl":"https://developer.qcloudimg.com/http-save/10011/65d7a38323ecc9174aa1bfd95907d17d.jpg","sourceType":99,"sourceDetail":{},"channelType":4,"channelDetail":{},"authorId":1577869,"columnId":2331,"columnIds":[],"writeTime":1735542670,"updateTime":1735542670,"viewCount":121,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://ask.qcloudimg.com/http-save/yehe-1577869/emq6640j7j.jpeg","company":"","introduce":"公众号：计算机视觉研究院","isProfessionVerified":0,"nickname":"计算机视觉研究院","title":"","uid":1577869,"id":1577869,"name":"计算机视觉研究院","avatar":"https://ask.qcloudimg.com/http-save/yehe-1577869/emq6640j7j.jpeg"},"tags":[{"tagId":17460,"tagName":"算法","id":17460,"name":"算法"},{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"},{"tagId":13755,"tagName":"gpt","id":13755,"name":"gpt"},{"tagId":17353,"tagName":"框架","id":17353,"name":"框架"},{"tagId":17440,"tagName":"数据","id":17440,"name":"数据"}]},{"id":2477802,"articleId":2477802,"title":"机器学习总结","content":"","plain":"","brief":"","summary":"无监督学习方法主要提到的是聚类。随机选定几个样本，通过一定的算法不停迭代直至收敛或者达到停止条件，然后便将所有样本分成了几类。","abstract":"无监督学习方法主要提到的是聚类。随机选定几个样本，通过一定的算法不停迭代直至收敛或者达到停止条件，然后便将所有样本分成了几类。","posterSummary":"","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-11217379/2aa1205acb5f8745294f8fc7955303a7.png","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-11217379/2aa1205acb5f8745294f8fc7955303a7.png","sourceType":99,"sourceDetail":{},"channelType":2,"channelDetail":{},"authorId":11217379,"columnId":103800,"columnIds":[],"writeTime":1734397933,"updateTime":1734397933,"viewCount":98,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/921bffda9eaacb11e05097f38ba8c27f.jpg","company":"山东省","introduce":"新一代电子信息专业","isProfessionVerified":0,"nickname":"zhangjiqun","title":"在读博士","uid":11217379,"id":11217379,"name":"zhangjiqun","avatar":"https://developer.qcloudimg.com/http-save/10011/921bffda9eaacb11e05097f38ba8c27f.jpg"},"tags":[{"tagId":10332,"tagName":"神经网络","id":10332,"name":"神经网络"},{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"},{"tagId":10722,"tagName":"线性回归","id":10722,"name":"线性回归"},{"tagId":17381,"tagName":"模型","id":17381,"name":"模型"},{"tagId":10149,"tagName":"机器学习","id":10149,"name":"机器学习"}]},{"id":2477045,"articleId":2477045,"title":"机器学习:什么是分类/回归/聚类/降维/决策","content":"","plain":"","brief":"","summary":"从强化学习的基本原理能看出它与其他机器学习算法如监督学习和非监督学习的一些基本差别。在监督学习和非监督学习中，数据是静态的、不需要与环境进行交互，比如图像识别，...","abstract":"从强化学习的基本原理能看出它与其他机器学习算法如监督学习和非监督学习的一些基本差别。在监督学习和非监督学习中，数据是静态的、不需要与环境进行交互，比如图像识别，...","posterSummary":"从强化学习的基本原理能看出它与其他机器学习算法如监督学习和非监督学习的一些基本差别。在监督学习和非监督学习中，数据是静态的、不需要与环境进行交互，比如图像识别，只要给出足够的差异样本，将数据输入深度神经网络中进行训练即可。","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-11217379/be1cdd55244693025c2a419a27d4fcf6.png","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-11217379/be1cdd55244693025c2a419a27d4fcf6.png","sourceType":99,"sourceDetail":{},"channelType":2,"channelDetail":{},"authorId":11217379,"columnId":103800,"columnIds":[],"writeTime":1734143094,"updateTime":1734143094,"viewCount":223,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/921bffda9eaacb11e05097f38ba8c27f.jpg","company":"山东省","introduce":"新一代电子信息专业","isProfessionVerified":0,"nickname":"zhangjiqun","title":"在读博士","uid":11217379,"id":11217379,"name":"zhangjiqun","avatar":"https://developer.qcloudimg.com/http-save/10011/921bffda9eaacb11e05097f38ba8c27f.jpg"},"tags":[{"tagId":17440,"tagName":"数据","id":17440,"name":"数据"},{"tagId":17460,"tagName":"算法","id":17460,"name":"算法"},{"tagId":10149,"tagName":"机器学习","id":10149,"name":"机器学习"},{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"},{"tagId":17188,"tagName":"变量","id":17188,"name":"变量"}]},{"id":2476999,"articleId":2476999,"title":"梯度下降求极值，机器学习&深度学习","content":"","plain":"","brief":"","summary":"导数也叫导函数，或者微商，它是微积分中的重要基础概念，从物理学角度来看，导数是研究物体某一时刻的瞬时速度，比如你开车从家 8:00 出发到公司上班，9:00 到...","abstract":"导数也叫导函数，或者微商，它是微积分中的重要基础概念，从物理学角度来看，导数是研究物体某一时刻的瞬时速度，比如你开车从家 8:00 出发到公司上班，9:00 到...","posterSummary":"导数也叫导函数，或者微商，它是微积分中的重要基础概念，从物理学角度来看，导数是研究物体某一时刻的瞬时速度，比如你开车从家 8:00 出发到公司上班，9:00 到到达公司，这一个小时内的平均车速是 80km/h，而途中8:15:30这一时刻的速度，就被称为瞬时速度，此刻的速度可能是 100km/h，也可能是 20km/h。而从几何意义上来讲，你可以把它理解为该函数曲线在一点上的切线斜率。\n\n 导数有...","description":"","picture":"https://developer.qcloudimg.com/http-save/yehe-11217379/9c945a3907d6fe54058f6d082a357633.png","coverImageUrl":"https://developer.qcloudimg.com/http-save/yehe-11217379/9c945a3907d6fe54058f6d082a357633.png","sourceType":99,"sourceDetail":{},"channelType":2,"channelDetail":{},"authorId":11217379,"columnId":103800,"columnIds":[],"writeTime":1734140762,"updateTime":1734140762,"viewCount":80,"likeCount":1,"commentCount":0,"favorCount":0,"weight":0,"status":2,"draftId":0,"tagIds":[],"isCommentEnable":true,"highQuality":false,"skipAds":false,"showAds":false,"focusRead":false,"publishTime":null,"editTime":null,"isCloseTextLink":false,"author":{"avatarUrl":"https://developer.qcloudimg.com/http-save/10011/921bffda9eaacb11e05097f38ba8c27f.jpg","company":"山东省","introduce":"新一代电子信息专业","isProfessionVerified":0,"nickname":"zhangjiqun","title":"在读博士","uid":11217379,"id":11217379,"name":"zhangjiqun","avatar":"https://developer.qcloudimg.com/http-save/10011/921bffda9eaacb11e05097f38ba8c27f.jpg"},"tags":[{"tagId":10539,"tagName":"人工智能","id":10539,"name":"人工智能"},{"tagId":10719,"tagName":"监督学习","id":10719,"name":"监督学习"},{"tagId":17290,"tagName":"函数","id":17290,"name":"函数"},{"tagId":10149,"tagName":"机器学习","id":10149,"name":"机器学习"},{"tagId":10333,"tagName":"深度学习","id":10333,"name":"深度学习"}]}]},"video":{"fetchStatus":"none","done":false,"nextPageNumber":1,"pageSize":20,"total":0,"list":[]}},"relatedProducts":[],"relatedDevdocs":[],"activeUsers":[],"hotColumns":[{"id":1014,"name":"腾讯云开发者社区头条","desc":"云头条，早报资讯。腾讯云开发者社区的管理动态和活动公告。","icon":"https://ask.qcloudimg.com/developer-images/column-icons/1014/675498/epnwv8386e.png","background":"https://imgcache.qq.com/qcloud/developer/images/release/column-bgs/1.svg","status":2,"creatorId":675498,"memberCount":2,"articleCount":444,"followCount":67512,"createdTime":1472197314,"creator":{"id":675498,"uid":675498,"name":"腾讯云开发者社区","label":"腾讯云开发者社区官方账号","avatar":"https://ask.qcloudimg.com/raw/yehe-b3360f6a89f75/eqohtul4uk.png","province":"1213","city":"1216","company":"腾讯云","title":"产品运营","school":"","major":"","homePage":"","region":1,"jobType":1,"graduationDate":"","education":0,"specialityIds":[10539,10244,10245,10333,10149],"specialities":[],"gender":1,"trade":"","growthLevel":0,"isProfessionVerified":true,"upvoteCount":43,"followingCount":5,"followerCount":2306,"questionCount":21,"answerCount":49,"followQuestionCount":0,"followTagCount":0,"favorAnswerCount":0,"beHandPickedCount":0,"followColumnCount":11,"articleCount":444,"validArticleCount":436}},{"id":1023,"name":"ArrayZoneYour的专栏","desc":"","icon":"https://imgcache.qq.com/qcloud/developer/images/release/column-icons/16.png","background":"https://imgcache.qq.com/qcloud/developer/images/release/column-bgs/5.svg","status":2,"creatorId":410635,"memberCount":1,"articleCount":17,"followCount":45,"createdTime":1474355584,"creator":{"id":410635,"uid":410635,"name":"ArrayZoneYour","label":": )","avatar":"https://ask.qcloudimg.com/avatar/410635/l23egjzhlb.jpg","province":"1001","city":"","company":"字节跳动","title":"前端开发","school":"华中科技大学","major":"","homePage":"https://arrayzoneyour.github.io","region":1,"jobType":1,"graduationDate":"","education":0,"specialityIds":[10169,10539,10149,10213,10198],"specialities":[],"gender":1,"trade":"","growthLevel":0,"isProfessionVerified":false,"upvoteCount":0,"followingCount":0,"followerCount":58,"questionCount":0,"answerCount":0,"followQuestionCount":0,"followTagCount":0,"favorAnswerCount":0,"beHandPickedCount":0,"followColumnCount":2,"articleCount":17,"validArticleCount":17}},{"id":1108,"name":"进击的Coder","desc":"","icon":"https://imgcache.qq.com/qcloud/developer/images/release/column-icons/15.png","background":"https://imgcache.qq.com/qcloud/developer/images/release/column-bgs/5.svg","status":2,"creatorId":223114,"memberCount":1,"articleCount":559,"followCount":201,"createdTime":1489064893,"creator":{"id":223114,"uid":223114,"name":"崔庆才","label":"","avatar":"https://ask.qcloudimg.com/http-save/yehe-223114/gdt81byrq8.jpeg","province":"1001","city":"","company":"微软","title":"工程师","school":"","major":"","homePage":"https://cuiqingcai.com","region":1,"jobType":1,"graduationDate":"","education":0,"specialityIds":[10169,10333,10678,10197],"specialities":[],"gender":1,"trade":"","growthLevel":0,"isProfessionVerified":false,"upvoteCount":0,"followingCount":3,"followerCount":294,"questionCount":0,"answerCount":0,"followQuestionCount":0,"followTagCount":0,"favorAnswerCount":0,"beHandPickedCount":0,"followColumnCount":3,"articleCount":567,"validArticleCount":559}},{"id":1172,"name":"腾讯云安全的专栏","desc":"","icon":"https://imgcache.qq.com/qcloud/developer/images/release/column-icons/11.png","background":"","status":2,"creatorId":881770,"memberCount":2,"articleCount":296,"followCount":94,"createdTime":1492132246,"creator":{"id":881770,"uid":881770,"name":"腾讯云安全","label":"","avatar":"https://ask.qcloudimg.com/http-save/yehe-881770/11cbda56f3b4f304d8a26ffbf05b7066.png","province":"","city":"","company":"","title":"","school":"","major":"","homePage":"","region":1,"jobType":1,"graduationDate":"","education":0,"specialityIds":[10539,10216,10149,10314,10251],"specialities":[],"gender":1,"trade":"","growthLevel":0,"isProfessionVerified":false,"upvoteCount":0,"followingCount":1,"followerCount":80,"questionCount":0,"answerCount":0,"followQuestionCount":0,"followTagCount":0,"favorAnswerCount":0,"beHandPickedCount":0,"followColumnCount":2,"articleCount":296,"validArticleCount":296}}],"recommendedTags":[],"env":"production","documentBaseTitle":"腾讯云开发者社区-腾讯云","cdnDomain":"cloudcache.tencent-cloud.cn","cssDomain":"cloudcache.tencent-cloud.cn","qcloudDomain":"cloud.tencent.com","consoleDomain":"console.cloud.tencent.com","qcommunity_identify_id":"X7tVGC3hjuYrRhxE1xsL2","session":{"isLogined":false,"isQcloudUser":false,"isOwner":false,"nickname":"","accountInfoCompleted":false,"phoneCompleted":false,"profile":{},"contactPhoneCompleted":false,"userInfo":{},"phoneMainland":false},"pvId":"-lXvC4Vb85AZDSwd6q4_4","userIp":"8.222.208.146","fromMiniProgram":false,"route":{"url":"/developer/tag/10719?entry=article","path":"/developer/tag/10719?entry=article","pathname":"/developer/tag/10719","search":"?entry=article","query":{"entry":"article"},"segments":["developer","tag","10719"]}}); </script><script class=""> if (!Element.prototype.matches) Element.prototype.matches = Element.prototype.msMatchesSelector || Element.prototype.webkitMatchesSelector; if (!Element.prototype.closest) Element.prototype.closest = function(s) { var el = this; if (!document.documentElement.contains(el)) return null; do { if (el.matches(s)) return el; el = el.parentElement; } while (el !== null); return null; }; window.addEventListener('mouseover', function(evt) { const target = evt.target; if (!target) { return; } const aEle = target.closest('a'); if (!aEle) { return; } let href = aEle.getAttribute('href'); if (!href) { return; } href = href.replace(/cloud.tencent.com.cn|cloud.tencent.com|cloud.tencent.cn/g, 'cloud.tencent.com'); aEle.setAttribute('href', href); }, true); </script></body></html>