<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>反向传播 on PlumePHP</title><link>https://plumephp.com/tags/%E5%8F%8D%E5%90%91%E4%BC%A0%E6%92%AD/</link><description>Recent content in 反向传播 on PlumePHP</description><generator>Hugo</generator><language>zh-CN</language><lastBuildDate>Thu, 13 Aug 2026 11:04:00 +0800</lastBuildDate><atom:link href="https://plumephp.com/tags/%E5%8F%8D%E5%90%91%E4%BC%A0%E6%92%AD/index.xml" rel="self" type="application/rss+xml"/><item><title>04. 神经网络基础</title><link>https://plumephp.com/ai-neural-networks-basics/</link><pubDate>Thu, 13 Aug 2026 11:04:00 +0800</pubDate><guid>https://plumephp.com/ai-neural-networks-basics/</guid><description>&lt;p&gt;神经网络是深度学习的基石。本文从感知机出发，逐步构建多层感知机 (MLP)，详解反向传播算法、激活函数选择、优化器对比与稳定训练的关键技巧。&lt;/p&gt;
&lt;h2 id="1-感知机与神经元模型"&gt;1. 感知机与神经元模型&lt;/h2&gt;
&lt;h3 id="11-感知机-perceptron"&gt;1.1 感知机 (Perceptron)&lt;/h3&gt;
&lt;p&gt;感知机是最简单的线性分类器：&lt;/p&gt;</description></item></channel></rss>