<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Continual Learning on Nalar</title>
    <link>https://nalar.dev/tags/continual-learning/</link>
    <description>Recent content in Continual Learning on Nalar</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 07 Sep 2026 00:00:00 +0700</lastBuildDate>
    <atom:link href="https://nalar.dev/tags/continual-learning/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Prevent Catastrophic Forgetting in Continual Learning</title>
      <link>https://nalar.dev/prevent-catastrophic-forgetting-in-continual-learning/</link>
      <pubDate>Mon, 07 Sep 2026 00:00:00 +0700</pubDate>
      <guid>https://nalar.dev/prevent-catastrophic-forgetting-in-continual-learning/</guid>
      <description>&lt;p&gt;Updating a neural network with new data sounds straightforward: continue training on the new examples and deploy the improved model. The difficulty is that an update which helps the new data can damage behavior the model learned earlier. A classifier that learns a new group of products, for example, may become worse at recognizing older groups even though those old classes never changed.&lt;/p&gt;&#xA;&lt;p&gt;This failure is called &lt;strong&gt;catastrophic forgetting&lt;/strong&gt;. It is especially important in continual learning, where a model learns from a sequence of tasks or data distributions instead of training once on a fixed mixed dataset.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
