<?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>神经网络训练 on Answer</title>
    <link>https://answer.freetools.me/tags/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E8%AE%AD%E7%BB%83/</link>
    <description>Recent content in 神经网络训练 on Answer</description>
    <generator>Hugo -- 0.152.2</generator>
    <language>zh-cn</language>
    <lastBuildDate>Thu, 12 Mar 2026 02:39:25 +0800</lastBuildDate>
    <atom:link href="https://answer.freetools.me/tags/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E8%AE%AD%E7%BB%83/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Teacher Forcing：为什么这个&#34;作弊&#34;技术统治了序列模型训练三十年</title>
      <link>https://answer.freetools.me/teacher-forcing%E4%B8%BA%E4%BB%80%E4%B9%88%E8%BF%99%E4%B8%AA%E4%BD%9C%E5%BC%8A%E6%8A%80%E6%9C%AF%E7%BB%9F%E6%B2%BB%E4%BA%86%E5%BA%8F%E5%88%97%E6%A8%A1%E5%9E%8B%E8%AE%AD%E7%BB%83%E4%B8%89%E5%8D%81%E5%B9%B4/</link>
      <pubDate>Thu, 12 Mar 2026 02:39:25 +0800</pubDate>
      <guid>https://answer.freetools.me/teacher-forcing%E4%B8%BA%E4%BB%80%E4%B9%88%E8%BF%99%E4%B8%AA%E4%BD%9C%E5%BC%8A%E6%8A%80%E6%9C%AF%E7%BB%9F%E6%B2%BB%E4%BA%86%E5%BA%8F%E5%88%97%E6%A8%A1%E5%9E%8B%E8%AE%AD%E7%BB%83%E4%B8%89%E5%8D%81%E5%B9%B4/</guid>
      <description>深入解析Teacher Forcing训练技术的本质、Exposure Bias问题的根源，以及三十年来研究者为解决这一困境所提出的各种方案。从Scheduled Sampling到Professor Forcing，从TeaForN到Minimum Risk Training，全面剖析序列模型训练的核心难题。</description>
    </item>
    <item>
      <title>Batch Size的选择：为什么这个超参数能决定模型的生死</title>
      <link>https://answer.freetools.me/batch-size%E7%9A%84%E9%80%89%E6%8B%A9%E4%B8%BA%E4%BB%80%E4%B9%88%E8%BF%99%E4%B8%AA%E8%B6%85%E5%8F%82%E6%95%B0%E8%83%BD%E5%86%B3%E5%AE%9A%E6%A8%A1%E5%9E%8B%E7%9A%84%E7%94%9F%E6%AD%BB/</link>
      <pubDate>Wed, 11 Mar 2026 23:43:13 +0800</pubDate>
      <guid>https://answer.freetools.me/batch-size%E7%9A%84%E9%80%89%E6%8B%A9%E4%B8%BA%E4%BB%80%E4%B9%88%E8%BF%99%E4%B8%AA%E8%B6%85%E5%8F%82%E6%95%B0%E8%83%BD%E5%86%B3%E5%AE%9A%E6%A8%A1%E5%9E%8B%E7%9A%84%E7%94%9F%E6%AD%BB/</guid>
      <description>深度解析神经网络训练中batch size选择背后的理论原理，从泛化差距到尖锐最小值，从梯度噪声到学习率缩放，揭示为什么小batch往往比大batch泛化更好。</description>
    </item>
  </channel>
</rss>
