<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Jacobian on 111qqz's blog</title><link>https://111qqz.com/en/tags/jacobian/</link><description>Recent content in Jacobian on 111qqz's blog</description><generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>hust.111qqz@gmail.com (111qqz)</managingEditor><webMaster>hust.111qqz@gmail.com (111qqz)</webMaster><copyright>© 2011-2026 111qqz</copyright><lastBuildDate>Sat, 12 Sep 2026 00:20:00 +0800</lastBuildDate><atom:link href="https://111qqz.com/en/tags/jacobian/index.xml" rel="self" type="application/rss+xml"/><item><title>从局部线性化到 RNN：理解 Jacobian 连乘</title><link>https://111qqz.com/en/post/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/2026-09-12-rnn-gradient-jacobian/</link><pubDate>Sat, 12 Sep 2026 00:20:00 +0800</pubDate><author>hust.111qqz@gmail.com (111qqz)</author><guid>https://111qqz.com/en/post/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/2026-09-12-rnn-gradient-jacobian/</guid><description>&lt;p&gt;最近在重拾一些深度学习基础，发现了一个很有意思的视角。&lt;/p&gt;
&lt;p&gt;以前在看 RNN（Recurrent Neural Network）的长距离梯度传播公式时，总能看到一堆 Jacobian 矩阵的连乘，比如 \(\frac{\partial h_T}{\partial h_0} = J_T J_{T-1} \dots J_1\)。&lt;/p&gt;</description></item></channel></rss>