<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Best-Practices on Neural Odyssey</title><link>https://danialjfz.github.io/myblog/tags/best-practices/</link><description>Recent content in Best-Practices on Neural Odyssey</description><generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>Danialj999@gmail.com (Danial Jafarzadeh)</managingEditor><webMaster>Danialj999@gmail.com (Danial Jafarzadeh)</webMaster><copyright>© 2026 Danial Jafarzadeh</copyright><lastBuildDate>Wed, 19 Nov 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://danialjfz.github.io/myblog/tags/best-practices/index.xml" rel="self" type="application/rss+xml"/><item><title>5 ML Mistakes I Made So You Don't Have To</title><link>https://danialjfz.github.io/myblog/posts/ml-mistakes-to-avoid/</link><pubDate>Wed, 19 Nov 2025 00:00:00 +0000</pubDate><author>Danialj999@gmail.com (Danial Jafarzadeh)</author><guid>https://danialjfz.github.io/myblog/posts/ml-mistakes-to-avoid/</guid><description>&lt;blockquote&gt;
&lt;p&gt;&lt;strong&gt;Abstract&lt;/strong&gt;&lt;br&gt;
This post is a checklist of failure modes that quietly ruin ML projects: bad data inspection, leakage, weak evaluation, class imbalance, and irreproducible experiments. The point is not to be dramatic about mistakes, but to make the debugging habits explicit before they cost days of work.&lt;/p&gt;</description></item></channel></rss>