<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>面试准备 on Answer</title>
    <link>https://answer.freetools.me/tags/%E9%9D%A2%E8%AF%95%E5%87%86%E5%A4%87/</link>
    <description>Recent content in 面试准备 on Answer</description>
    <generator>Hugo -- 0.152.2</generator>
    <language>zh-cn</language>
    <lastBuildDate>Thu, 12 Mar 2026 18:36:22 +0800</lastBuildDate>
    <atom:link href="https://answer.freetools.me/tags/%E9%9D%A2%E8%AF%95%E5%87%86%E5%A4%87/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Self-Attention计算全解：从矩阵乘法到梯度流动的完整技术解析</title>
      <link>https://answer.freetools.me/self-attention%E8%AE%A1%E7%AE%97%E5%85%A8%E8%A7%A3%E4%BB%8E%E7%9F%A9%E9%98%B5%E4%B9%98%E6%B3%95%E5%88%B0%E6%A2%AF%E5%BA%A6%E6%B5%81%E5%8A%A8%E7%9A%84%E5%AE%8C%E6%95%B4%E6%8A%80%E6%9C%AF%E8%A7%A3%E6%9E%90/</link>
      <pubDate>Thu, 12 Mar 2026 18:36:22 +0800</pubDate>
      <guid>https://answer.freetools.me/self-attention%E8%AE%A1%E7%AE%97%E5%85%A8%E8%A7%A3%E4%BB%8E%E7%9F%A9%E9%98%B5%E4%B9%98%E6%B3%95%E5%88%B0%E6%A2%AF%E5%BA%A6%E6%B5%81%E5%8A%A8%E7%9A%84%E5%AE%8C%E6%95%B4%E6%8A%80%E6%9C%AF%E8%A7%A3%E6%9E%90/</guid>
      <description>深入解析Transformer中Self-Attention的完整计算流程，从Query/Key/Value的直观含义到多头注意力的实现细节，涵盖注意力分数计算、缩放原理、掩码机制、残差连接等核心技术，以及面试高频考点与常见误区。</description>
    </item>
  </channel>
</rss>
