<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Deep-Learning on Behnoud Nakhostin</title>
    <link>https://behnoudng.com/tags/deep-learning/</link>
    <description>Recent content in Deep-Learning on Behnoud Nakhostin</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 15 Dec 2025 16:46:42 +0000</lastBuildDate>
    <atom:link href="https://behnoudng.com/tags/deep-learning/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Training VS Fine Tuning</title>
      <link>https://behnoudng.com/posts/training-vs-fine-tuning/</link>
      <pubDate>Mon, 15 Dec 2025 16:46:42 +0000</pubDate>
      <guid>https://behnoudng.com/posts/training-vs-fine-tuning/</guid>
      <description>&lt;h1 id=&#34;training-vs-fine-tuning&#34;&gt;Training vs Fine-Tuning&lt;/h1&gt;&#xA;&lt;p&gt;When I first started learning about fine‑tuning an already trained model, meaning a pretrained model, I found it hard to clearly see how it differs from training a model from scratch. The code for both is usually very similar, and the overall process looks almost the same.&lt;/p&gt;&#xA;&lt;p&gt;The key difference between training from scratch and fine‑tuning a pretrained model is how the weights are initialized. When we fine‑tune a model, we start from weights that already capture useful patterns instead of initializing everything randomly. In other words, the model does not begin from zero knowledge.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
