<?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>SVD on 3rd layer</title><link>https://3rdlayer.uk/tags/svd/</link><description>Recent content in SVD on 3rd layer</description><generator>Hugo -- 0.157.0</generator><language>en-US</language><lastBuildDate>Sun, 27 Sep 2026 09:00:00 +0900</lastBuildDate><atom:link href="https://3rdlayer.uk/tags/svd/index.xml" rel="self" type="application/rss+xml"/><item><title>Trajectory ML 02: PCA as the First Latent Space</title><link>https://3rdlayer.uk/posts/trajectory-ml-02-pca/</link><pubDate>Sun, 27 Sep 2026 09:00:00 +0900</pubDate><guid>https://3rdlayer.uk/posts/trajectory-ml-02-pca/</guid><description>Derive PCA from reconstruction and variance, connect covariance eigenvectors to SVD, and evaluate compression on unseen sessions.</description></item></channel></rss>