<?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>归纳偏好 on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/%E5%BD%92%E7%BA%B3%E5%81%8F%E5%A5%BD/</link><description>Recent content in 归纳偏好 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>Wed, 21 Oct 2026 07:12:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%BD%92%E7%BA%B3%E5%81%8F%E5%A5%BD/index.xml" rel="self" type="application/rss+xml"/><item><title>大模型的归纳偏好：架构里藏着哪些我们没明说的假设</title><link>https://guijiagi.com/posts/2026-10-21-02-inductive-bias-built-in-architecture/</link><pubDate>Wed, 21 Oct 2026 07:12:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-21-02-inductive-bias-built-in-architecture/</guid><description>没有写进数据的偏好藏在网络结构里，这些先验决定了模型把世界看成什么形状</description></item></channel></rss>