<?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>Autoencoder on 3rd layer</title><link>https://3rdlayer.uk/ko/tags/autoencoder/</link><description>Recent content in Autoencoder on 3rd layer</description><generator>Hugo -- 0.157.0</generator><language>ko-KR</language><lastBuildDate>Sun, 27 Sep 2026 09:00:00 +0900</lastBuildDate><atom:link href="https://3rdlayer.uk/ko/tags/autoencoder/index.xml" rel="self" type="application/rss+xml"/><item><title>Trajectory ML 03: Autoencoder와 VAE, 좋은 상태란 무엇인가</title><link>https://3rdlayer.uk/ko/posts/trajectory-ml-03-representation/</link><pubDate>Sun, 27 Sep 2026 09:00:00 +0900</pubDate><guid>https://3rdlayer.uk/ko/posts/trajectory-ml-03-representation/</guid><description>PCA, 오토인코더, VAE를 같은 데이터에 학습시킨다. ELBO와 재매개변수화를 이해하고, 복원을 잘하는 것과 의미 있는 상태를 찾는 것을 구분한다.</description></item></channel></rss>