<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/">
	<channel>
		<title><![CDATA[MKLab - LECTURES]]></title>
		<link>https://mklab.gr/</link>
		<description><![CDATA[MKLab - https://mklab.gr]]></description>
		<pubDate>Sat, 17 Oct 2026 11:46:51 +0000</pubDate>
		<generator>MyBB</generator>
		<item>
			<title><![CDATA[The Geometry of Neural Networks]]></title>
			<link>https://mklab.gr/showthread.php?tid=2051</link>
			<pubDate>Sun, 20 Sep 2026 01:15:55 +0300</pubDate>
			<dc:creator><![CDATA[<a href="https://mklab.gr/member.php?action=profile&uid=1">mklabgr</a>]]></dc:creator>
			<guid isPermaLink="false">https://mklab.gr/showthread.php?tid=2051</guid>
			<description><![CDATA[<span style="color: #1f1f1f;" class="mycode_color"><span style="font-family: 'Google Sans Text', sans-serif;" class="mycode_font">This lecture introduces an academic reading course focused on the geometric and mathematical foundations of neural networks, known as neuromanifolds. The speaker outlines the course structure—which spans from basic feed-forward architectures to advanced topics in information geometry and algebraic geometry—while highlighting minimal prerequisites and organizing student presentation sign-ups. </span></span><br />
<br />
<span style="color: #1f1f1f;" class="mycode_color"><span style="font-family: 'Google Sans Text', sans-serif;" class="mycode_font">By exploring how parameters map to function spaces and analyzing concepts like singularities and expressivity, the course aims to provide mathematicians and researchers with rigorous tools to better understand and evaluate modern machine learning architectures.</span></span><br />
<br />
<br />
<a href="https://www.youtube.com/watch?v=PmHCP_sLbGM" target="_blank" rel="noopener" class="mycode_url">LECTURE</a>]]></description>
			<content:encoded><![CDATA[<span style="color: #1f1f1f;" class="mycode_color"><span style="font-family: 'Google Sans Text', sans-serif;" class="mycode_font">This lecture introduces an academic reading course focused on the geometric and mathematical foundations of neural networks, known as neuromanifolds. The speaker outlines the course structure—which spans from basic feed-forward architectures to advanced topics in information geometry and algebraic geometry—while highlighting minimal prerequisites and organizing student presentation sign-ups. </span></span><br />
<br />
<span style="color: #1f1f1f;" class="mycode_color"><span style="font-family: 'Google Sans Text', sans-serif;" class="mycode_font">By exploring how parameters map to function spaces and analyzing concepts like singularities and expressivity, the course aims to provide mathematicians and researchers with rigorous tools to better understand and evaluate modern machine learning architectures.</span></span><br />
<br />
<br />
<a href="https://www.youtube.com/watch?v=PmHCP_sLbGM" target="_blank" rel="noopener" class="mycode_url">LECTURE</a>]]></content:encoded>
		</item>
	</channel>
</rss>