<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Mutual Learning on 111qqz's blog</title><link>https://111qqz.com/en/tags/mutual-learning/</link><description>Recent content in Mutual Learning on 111qqz's blog</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2015-2026 111qqz</copyright><lastBuildDate>Sun, 18 Feb 2018 10:46:35 +0000</lastBuildDate><atom:link href="https://111qqz.com/en/tags/mutual-learning/index.xml" rel="self" type="application/rss+xml"/><item><title>Deep Mutual Learning（相互学习） 阅读笔记</title><link>https://111qqz.com/en/post/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/%E8%AE%A1%E7%AE%97%E6%9C%BA%E8%A7%86%E8%A7%89/2018-02-18-deep-mutual-learning-notes/</link><pubDate>Sun, 18 Feb 2018 10:46:35 +0000</pubDate><guid>https://111qqz.com/en/post/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/%E8%AE%A1%E7%AE%97%E6%9C%BA%E8%A7%86%E8%A7%89/2018-02-18-deep-mutual-learning-notes/</guid><description>&lt;p&gt;&lt;a href="https://arxiv.org/abs/1706.00384" target="_blank" rel="noreferrer"&gt;原始论文&lt;/a&gt;&lt;/p&gt;
&lt;p&gt;DNN在很多问题上效果很不错，但是由于深度和宽度过大，导致需要的执行时间和内存过大。我们需要讨论一些能快速执行并且对内存的需要不大的模型。&lt;/p&gt;</description></item></channel></rss>