<?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>Normalizations on Hojae Lee</title><link>https://hojaeklee.github.io/tags/normalizations/</link><description>Recent content in Normalizations on Hojae Lee</description><generator>Hugo -- 0.160.1</generator><language>en</language><lastBuildDate>Mon, 28 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://hojaeklee.github.io/tags/normalizations/index.xml" rel="self" type="application/rss+xml"/><item><title>The Normalizations I wanted to look into</title><link>https://hojaeklee.github.io/til/deep_learning/20260928_normalizations/</link><pubDate>Mon, 28 Sep 2026 00:00:00 +0000</pubDate><guid>https://hojaeklee.github.io/til/deep_learning/20260928_normalizations/</guid><description>&lt;p&gt;After my &lt;a href="https://hojaeklee.github.io/til/deep_learning/20260927_swish_and_swiglu/"&gt;Swish and SwiGLU&lt;/a&gt;
adventure, I wanted to do another set of chronological reading, this time on normalization techniques. Much like the activation functions, these are very commonplace in deep learning architecture, but beyond BatchNorm I hadn&amp;rsquo;t sat down to read these as a group to parse out the use cases and the limitations that subsequent techniques answer.&lt;/p&gt;</description></item></channel></rss>