<?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>自由能原理 on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/%E8%87%AA%E7%94%B1%E8%83%BD%E5%8E%9F%E7%90%86/</link><description>Recent content in 自由能原理 on AI 实战派 · 从技术到赚钱</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Tue, 20 Oct 2026 12:42:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E8%87%AA%E7%94%B1%E8%83%BD%E5%8E%9F%E7%90%86/index.xml" rel="self" type="application/rss+xml"/><item><title>自由能原理与深度学习：主动推理是不是另一套学习语言</title><link>https://guijiagi.com/posts/2026-10-20-07-free-energy-principle-active-inference/</link><pubDate>Tue, 20 Oct 2026 12:42:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-20-07-free-energy-principle-active-inference/</guid><description>自由能原理把生命描述为最小化意外的自我维持，它与变分深度学习在数学上同源，关切却不同</description></item></channel></rss>