<?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>Automl on Sagar's Notes</title><link>https://sagsan.com/tags/automl/</link><description>Recent content in Automl on Sagar's Notes</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Tue, 28 Jul 2026 00:00:00 -0700</lastBuildDate><atom:link href="https://sagsan.com/tags/automl/index.xml" rel="self" type="application/rss+xml"/><item><title>Transfer Learning II: You Probably Don't Need to Build Your Own Model</title><link>https://sagsan.com/writing/you-probably-dont-need-to-build-your-own-model/</link><pubDate>Tue, 28 Jul 2026 00:00:00 -0700</pubDate><guid>https://sagsan.com/writing/you-probably-dont-need-to-build-your-own-model/</guid><description>A custom MobileNetV2 took two weekends. Vertex AI AutoML reached the same F1 score for about $5.</description></item></channel></rss>