<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Math Lucas Versini &#8211; FAU DCN-AvH</title>
	<atom:link href="https://dcn.nat.fau.eu/category/math/posts-lucas-versini/feed/" rel="self" type="application/rss+xml" />
	<link>https://dcn.nat.fau.eu</link>
	<description>Chair for Dynamics, Control, Machine Learning and Numerics -Alexander von Humboldt Professorship</description>
	<lastBuildDate>Mon, 20 Jul 2026 15:27:46 +0000</lastBuildDate>
	<language>en-US</language>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	<generator>https://wordpress.org/?v=7.1</generator>

<image>
	<url>https://dcn.nat.fau.eu/wp-content/uploads/cropped-FAUDCNAvHlogo_square_silhouette_512x512-32x32.png</url>
	<title>Math Lucas Versini &#8211; FAU DCN-AvH</title>
	<link>https://dcn.nat.fau.eu</link>
	<width>32</width>
	<height>32</height>
</image> 
	<item>
		<title>Clustering in discrete-time self-attention</title>
		<link>https://dcn.nat.fau.eu/clustering-in-discrete-time-self-attention/</link>
		
		<dc:creator><![CDATA[darlis.dcn]]></dc:creator>
		<pubDate>Thu, 30 Jan 2025 16:13:31 +0000</pubDate>
				<category><![CDATA[Math]]></category>
		<category><![CDATA[Math Lucas Versini]]></category>
		<guid isPermaLink="false">https://dcn.nat.fau.eu/?p=30400</guid>

					<description><![CDATA[Clustering in discrete-time self-attention Since the article Attention Is All You Need [1] published in 2017, many Deep Learning models adopt the architecture of Transformers, especially for Natural Language Processing and sequence modeling. These Transformers are essentially composed of layers, alternating between self-attention layers and feed forward layers, with normalization in-between. In this post, we [&#8230;]]]></description>
		
		
		
			</item>
		<item>
		<title>Generalization bounds for neural ODEs: A user-friendly guide</title>
		<link>https://dcn.nat.fau.eu/generalization-bounds-for-neural-odes-a-user-friendly-guide/</link>
		
		<dc:creator><![CDATA[darlis.dcn]]></dc:creator>
		<pubDate>Tue, 06 Aug 2024 09:20:15 +0000</pubDate>
				<category><![CDATA[Math]]></category>
		<category><![CDATA[Math Lucas Versini]]></category>
		<guid isPermaLink="false">https://dcn.nat.fau.eu/?p=29667</guid>

					<description><![CDATA[Generalization bounds for neural ODEs: A user-friendly guide Once a neural network is trained, how can one measure its performance on new, unseen data? This concept is known as generalization. While many theoretical models exist, practical models often lack comprehensive generalization results. This post introduces a probabilistic approach to quantify the error of a model [&#8230;]]]></description>
		
		
		
			</item>
	</channel>
</rss>
