<?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>Research-Practice on Quang Minh Dinh</title>
    <link>https://quangminhdinh.github.io/tags/research-practice/</link>
    <description>Recent content in Research-Practice on Quang Minh Dinh</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 22 Jun 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://quangminhdinh.github.io/tags/research-practice/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Read the data before you add machinery</title>
      <link>https://quangminhdinh.github.io/garden/read-the-data-first/</link>
      <pubDate>Mon, 15 Jun 2026 00:00:00 +0000</pubDate>
      <guid>https://quangminhdinh.github.io/garden/read-the-data-first/</guid>
      <description>Supervision and structure are often already in the dataset, hiding in plain sight. The second vehicle in a sentence was free labels.</description>
    </item>
    <item>
      <title>The test distribution is the only one that counts</title>
      <link>https://quangminhdinh.github.io/garden/the-test-distribution-is-the-only-one-that-counts/</link>
      <pubDate>Sat, 30 May 2026 00:00:00 +0000</pubDate>
      <guid>https://quangminhdinh.github.io/garden/the-test-distribution-is-the-only-one-that-counts/</guid>
      <description>A strong validation number can be a trap. My clearest version of this lesson came from a 0.58 that became a 0.35.</description>
    </item>
  </channel>
</rss>
