<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Transformer on 🌸沐雪-medicago🎀</title>
    <link>https://8d2d5c12.hugo-blog-asi.pages.dev/tags/transformer/</link>
    <description>Recent content from 🌸沐雪-medicago🎀</description>
    <generator>Hugo</generator>
    <language>en-US</language>
    
    <managingEditor>medicago.19@outlook.com (medicago)</managingEditor>
    <webMaster>medicago.19@outlook.com (medicago)</webMaster>
    
    <copyright>All articles on this blog are licensed under the BY-NC-SA license agreement unless otherwise stated. Please indicate the source when reprinting!</copyright>
    
    <lastBuildDate>Tue, 15 Sep 2026 01:33:43 +0800</lastBuildDate>
    
    
    <atom:link href="https://8d2d5c12.hugo-blog-asi.pages.dev/tags/transformer/index.xml" rel="self" type="application/rss&#43;xml" />
    

    
    

    <item>
      <title>从词向量到 Transformer：RNN、CNN、Self-Attention 与 QKV 的系统理解</title>
      <link>https://8d2d5c12.hugo-blog-asi.pages.dev/post/word-embeddings-to-transformer/</link>
      <pubDate>Tue, 15 Sep 2026 01:33:43 &#43;0800</pubDate>
      <author>medicago.19@outlook.com (medicago)</author>
      <guid>https://8d2d5c12.hugo-blog-asi.pages.dev/post/word-embeddings-to-transformer/</guid>
      <description>
        <![CDATA[<h1>从词向量到 Transformer：RNN、CNN、Self-Attention 与 QKV 的系统理解</h1><p>Author: medicago(medicago.19@outlook.com)</p>
        
          <blockquote>
<p><strong>阅读主线：</strong> Embedding 解决“怎样表示”，Attention 解决“从哪里获取信息”，Value 的加权和完成“信息聚合”。本文以 <code>Tom loves his dog</code> 为例，把这些概念串成一条完整的计算链。</p>
        
        <hr><p>Published on 2026-09-15 at <a href='https://8d2d5c12.hugo-blog-asi.pages.dev/'>🌸沐雪-medicago🎀</a>, last modified on 2026-09-15</p>]]>
      </description>
      
        <category>人工智能</category>
      
    </item>
    
  </channel>
</rss>
