<?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>灾难性遗忘 on Answer</title>
    <link>https://answer.freetools.me/tags/%E7%81%BE%E9%9A%BE%E6%80%A7%E9%81%97%E5%BF%98/</link>
    <description>Recent content in 灾难性遗忘 on Answer</description>
    <generator>Hugo -- 0.152.2</generator>
    <language>zh-cn</language>
    <lastBuildDate>Mon, 09 Mar 2026 07:29:58 +0800</lastBuildDate>
    <atom:link href="https://answer.freetools.me/tags/%E7%81%BE%E9%9A%BE%E6%80%A7%E9%81%97%E5%BF%98/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>为什么神经网络学会了新知识就会忘记旧知识：从灾难性遗忘到持续学习的技术突围</title>
      <link>https://answer.freetools.me/%E4%B8%BA%E4%BB%80%E4%B9%88%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E5%AD%A6%E4%BC%9A%E4%BA%86%E6%96%B0%E7%9F%A5%E8%AF%86%E5%B0%B1%E4%BC%9A%E5%BF%98%E8%AE%B0%E6%97%A7%E7%9F%A5%E8%AF%86%E4%BB%8E%E7%81%BE%E9%9A%BE%E6%80%A7%E9%81%97%E5%BF%98%E5%88%B0%E6%8C%81%E7%BB%AD%E5%AD%A6%E4%B9%A0%E7%9A%84%E6%8A%80%E6%9C%AF%E7%AA%81%E5%9B%B4/</link>
      <pubDate>Mon, 09 Mar 2026 07:29:58 +0800</pubDate>
      <guid>https://answer.freetools.me/%E4%B8%BA%E4%BB%80%E4%B9%88%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E5%AD%A6%E4%BC%9A%E4%BA%86%E6%96%B0%E7%9F%A5%E8%AF%86%E5%B0%B1%E4%BC%9A%E5%BF%98%E8%AE%B0%E6%97%A7%E7%9F%A5%E8%AF%86%E4%BB%8E%E7%81%BE%E9%9A%BE%E6%80%A7%E9%81%97%E5%BF%98%E5%88%B0%E6%8C%81%E7%BB%AD%E5%AD%A6%E4%B9%A0%E7%9A%84%E6%8A%80%E6%9C%AF%E7%AA%81%E5%9B%B4/</guid>
      <description>深入解析神经网络灾难性遗忘问题的本质、历史沿革与解决方案。从1989年McCloskey和Cohen的经典发现，到2017年EWC方法的突破，再到LLM时代的LoRA与O-LoRA技术演进。系统阐述回放方法、正则化方法、梯度约束和参数隔离四大技术路线，揭示稳定性-可塑性困境的数学本质，以及大模型时代持续学习面临的全新挑战。</description>
    </item>
  </channel>
</rss>
