<?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>深度学习基础 on Arden’s blog</title><link>https://ardenj.pages.dev/series/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E5%9F%BA%E7%A1%80/</link><description>Recent content in 深度学习基础 on Arden’s blog</description><generator>Hugo -- 0.147.7</generator><language>zh-cn</language><lastBuildDate>Sat, 11 Jul 2026 00:00:00 +0800</lastBuildDate><atom:link href="https://ardenj.pages.dev/series/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E5%9F%BA%E7%A1%80/index.xml" rel="self" type="application/rss+xml"/><item><title>手撕损失函数：交叉熵（CE / BCE）</title><link>https://ardenj.pages.dev/learning/cross-entropy-ce-bce/</link><pubDate>Sat, 11 Jul 2026 00:00:00 +0800</pubDate><guid>https://ardenj.pages.dev/learning/cross-entropy-ce-bce/</guid><description>从信息量、信息熵与 KL 散度出发，推导交叉熵，并梳理 BCE 与 CE 的区别。</description></item></channel></rss>