<?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>Swish on Hojae Lee</title><link>https://hojaeklee.github.io/tags/swish/</link><description>Recent content in Swish on Hojae Lee</description><generator>Hugo -- 0.160.1</generator><language>en</language><lastBuildDate>Sun, 27 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://hojaeklee.github.io/tags/swish/index.xml" rel="self" type="application/rss+xml"/><item><title>Swish and SwiGLU</title><link>https://hojaeklee.github.io/til/deep_learning/20260927_swish_and_swiglu/</link><pubDate>Sun, 27 Sep 2026 00:00:00 +0000</pubDate><guid>https://hojaeklee.github.io/til/deep_learning/20260927_swish_and_swiglu/</guid><description>&lt;p&gt;Yesterday I had the joy of randomly reading papers that introduced &lt;a href="https://www.alphaxiv.org/abs/1710.05941" target="_blank" rel="noopener noreferrer"&gt;Swish&lt;/a&gt;
and &lt;a href=""&gt;SwiGLU&lt;/a&gt;
. Recently, I decided I wanted to update my knowledge of deep learning from around 2020, when I pivoted slightly more towards generative models (diffusion and GANs) and neuroscience to complete my PhD. I knew there were a lot of exciting things coming out that I&amp;rsquo;ve heard of, but haven&amp;rsquo;t had a chance to sit down and read.&lt;/p&gt;</description></item></channel></rss>