<?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>Posts on ML Learning Notes</title><link>https://omegazhang3.github.io/ml-blog/posts/</link><description>Recent content in Posts on ML Learning Notes</description><generator>Hugo -- 0.125.7</generator><language>en-us</language><lastBuildDate>Sun, 04 Oct 2026 12:21:03 +0000</lastBuildDate><atom:link href="https://omegazhang3.github.io/ml-blog/posts/index.xml" rel="self" type="application/rss+xml"/><item><title>深入理解 Softmax 函数：原理、公式与实战</title><link>https://omegazhang3.github.io/ml-blog/posts/softmax/</link><pubDate>Sun, 04 Oct 2026 12:21:03 +0000</pubDate><guid>https://omegazhang3.github.io/ml-blog/posts/softmax/</guid><description>&lt;blockquote>
&lt;p>Softmax 是深度学习中最经典的函数之一，几乎所有多分类模型的输出层都少不了它。本文将从原理、数学公式、代码实现到实际应用，带你彻底搞懂 Softmax。&lt;/p>
&lt;/blockquote></description></item><item><title>Linear Regression from Scratch</title><link>https://omegazhang3.github.io/ml-blog/posts/linear-regression/</link><pubDate>Sun, 04 Oct 2026 00:00:00 +0000</pubDate><guid>https://omegazhang3.github.io/ml-blog/posts/linear-regression/</guid><description>Deriving linear regression and implementing gradient descent in NumPy.</description></item></channel></rss>