<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title>Self-Supervised Learning - Tag - Xiaopeng Xu</title><link>https://xu-xp.com/tags/self-supervised-learning/</link><description>Self-Supervised Learning - Tag - Xiaopeng Xu</description><generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>xiaopeng.xu@kaust.edu.sa (Xiaopeng Xu)</managingEditor><webMaster>xiaopeng.xu@kaust.edu.sa (Xiaopeng Xu)</webMaster><lastBuildDate>Thu, 07 Jan 2021 00:00:00 +0000</lastBuildDate><atom:link href="https://xu-xp.com/tags/self-supervised-learning/" rel="self" type="application/rss+xml"/><item><title>CL 对比学习介绍</title><link>https://xu-xp.com/posts/contrastive_learn/</link><pubDate>Thu, 07 Jan 2021 00:00:00 +0000</pubDate><author>xiaopeng.xu@kaust.edu.sa (Xiaopeng Xu)</author><guid>https://xu-xp.com/posts/contrastive_learn/</guid><description><![CDATA[<h2 id="对比学习简介-2021-01-07">对比学习简介 2021-01-07</h2>
<p>参考：Understanding Contrastive Learning <a href="https://towardsdatascience.com/understanding-contrastive-learning-d5b19fd96607" target="_blank" rel="noopener noreffer ">https://towardsdatascience.com/understanding-contrastive-learning-d5b19fd96607</a></p>
<p>对比学习是一种机器学习技术，通过教导数据点相似或不同，让模型无需标签就能学习到数据集的一般特征。</p>
<p>背景：和 word2vec 类似，将样本投射到另一个空间维度，成为一个 vector，相似的样本 cosine 距离小，不相似的距离大。</p>]]></description></item></channel></rss>