<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI Theory on The Coders Blog</title><link>https://thecodersblog.com/tag/ai-theory/</link><description>Recent content in AI Theory on The Coders Blog</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 06 May 2026 22:07:47 +0000</lastBuildDate><atom:link href="https://thecodersblog.com/tag/ai-theory/index.xml" rel="self" type="application/rss+xml"/><item><title>A Theory of Deep Learning: Understanding the Fundamentals</title><link>https://thecodersblog.com/a-theory-of-deep-learning-2026/</link><pubDate>Wed, 06 May 2026 22:07:47 +0000</pubDate><guid>https://thecodersblog.com/a-theory-of-deep-learning-2026/</guid><description>&lt;p&gt;The practice of deep learning has long outpaced its theoretical underpinnings, leaving us with a powerful toolset that often feels more like sophisticated alchemy than rigorous science. We can train models that achieve superhuman performance, yet the fundamental reasons for their generalization, especially in the face of extreme overparameterization, remain elusive, forcing us to rely on empirical risk minimization and the hope that it won&amp;rsquo;t spectacularly fail. This gap is precisely what Elon Litman&amp;rsquo;s recent work seeks to bridge, proposing a radical shift in how we analyze and understand neural networks.&lt;/p&gt;</description></item></channel></rss>