<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>逻辑回归 on Pdch's log</title><link>https://pdch.codeberg.page/tags/%E9%80%BB%E8%BE%91%E5%9B%9E%E5%BD%92/</link><description>Recent content in 逻辑回归 on Pdch's log</description><generator>Hugo</generator><language>zh-CN</language><lastBuildDate>Thu, 30 Jul 2026 00:30:00 +0800</lastBuildDate><atom:link href="https://pdch.codeberg.page/tags/%E9%80%BB%E8%BE%91%E5%9B%9E%E5%BD%92/index.xml" rel="self" type="application/rss+xml"/><item><title>PRML 第四章：线性分类模型 — 从决策边界到贝叶斯逻辑回归</title><link>https://pdch.codeberg.page/blog/2026-07-30-linear-classification/</link><pubDate>Thu, 30 Jul 2026 00:30:00 +0800</pubDate><guid>https://pdch.codeberg.page/blog/2026-07-30-linear-classification/</guid><description>&lt;h1 id="prml-第四章线性分类模型"&gt;PRML 第四章：线性分类模型&lt;/h1&gt;
&lt;p&gt;第三章里，我们用线性模型预测连续值；现在把目标换成离散类别。看起来只是把输出从 $\mathbb{R}$ 换成 $\{0,1\}$，实际却带来三个新问题：&lt;/p&gt;</description></item></channel></rss>