<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title>All All Posts - lilfry's library</title><link>https://lilfry09.github.io/en/posts/</link><description>All All Posts | lilfry's library</description><generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>lilfry@sjtu.edu.cn (lilfry)</managingEditor><webMaster>lilfry@sjtu.edu.cn (lilfry)</webMaster><copyright>All rights reserved.</copyright><atom:link href="https://lilfry09.github.io/en/posts/" rel="self" type="application/rss+xml"/><item><title>Quantum Physics &amp; Quantum Mechanics — Review Notes</title><link>https://lilfry09.github.io/en/posts/quantum-physics-review-en/</link><pubDate>Wed, 27 May 2026 12:00:00 +0800</pubDate><author>fry</author><guid>https://lilfry09.github.io/en/posts/quantum-physics-review-en/</guid><description>Complete review notes for SJTU College Physics III: Quantum Mechanics, with 350+ practice problems.</description></item><item><title>Deep learning optimization algorithm</title><link>https://lilfry09.github.io/en/posts/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E4%BC%98%E5%8C%96%E7%AE%97%E6%B3%95/</link><pubDate>Tue, 02 Sep 2025 13:20:08 +0800</pubDate><author>fry</author><guid>https://lilfry09.github.io/en/posts/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E4%BC%98%E5%8C%96%E7%AE%97%E6%B3%95/</guid><description><![CDATA[<h2 id="deep-learning-optimization-algorithms-sgd-rmsprop-adagrad-adam-detailed-explanation">Deep learning optimization algorithms: SGD, RMSProp, AdaGrad, Adam detailed explanation</h2>
<p>In the training process of deep learning, optimization algorithms play a crucial role. They determine how the model parameters are updated according to the gradient of the loss function, thus affecting the model&rsquo;s convergence speed and final performance. This article will introduce in depth several of the most commonly used and basic optimization algorithms: SGD, RMSProp, AdaGrad and Adam, and analyze their formulas, advantages and disadvantages.</p>]]></description></item><item><title>How to build your own blog with hugo</title><link>https://lilfry09.github.io/en/posts/%E5%A6%82%E4%BD%95%E7%94%A8hugo%E6%9E%84%E5%BB%BA%E8%87%AA%E5%B7%B1%E7%9A%84%E5%8D%9A%E5%AE%A2/</link><pubDate>Mon, 31 Mar 2025 13:45:08 +0800</pubDate><author>fry</author><guid>https://lilfry09.github.io/en/posts/%E5%A6%82%E4%BD%95%E7%94%A8hugo%E6%9E%84%E5%BB%BA%E8%87%AA%E5%B7%B1%E7%9A%84%E5%8D%9A%E5%AE%A2/</guid><description><![CDATA[<h1 id="who-is-this-written-for">Who is this written for?</h1>
<p>If you also want to start your own blog and hope to:</p>
<ul>
<li>The source code is placed in a warehouse so that you can write it slowly</li>
<li>The final website is automatically deployed to <code>yourusername.github.io</code></li>
<li>Try to avoid the pitfalls of GitHub Pages and Hugo as much as possible</li>
</ul>
<p>Then this process will be easier.</p>
<p>I am using two warehouses here:</p>
<ul>
<li>Private warehouse: <code>blogsource</code></li>
<li>Public warehouse: <code>yourusername.github.io</code></li>
</ul>
<p>Among them, it is best to use <code>yourusername.github.io</code> directly as the name of the public warehouse. If it is your first time to use GitHub Pages, it is recommended to follow this step, which is the easiest.</p>]]></description></item></channel></rss>