<?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>Hub</title>
	<atom:link href="https://dcn.nat.fau.eu/category/hub/feed/" rel="self" type="application/rss+xml" />
	<link>https://dcn.nat.fau.eu</link>
	<description>FAU DCN-AvH. Chair for Dynamics, Control, Machine Learning and Numerics -Alexander von Humboldt Professorship</description>
	<lastBuildDate>Fri, 14 Nov 2025 17:27:04 +0000</lastBuildDate>
	<language>en-US</language>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	<generator>https://wordpress.org/?v=7.0</generator>

<image>
	<url>https://dcn.nat.fau.eu/wp-content/uploads/cropped-FAUDCNAvHlogo_square_silhouette_512x512-32x32.png</url>
	<title>Hub</title>
	<link>https://dcn.nat.fau.eu</link>
	<width>32</width>
	<height>32</height>
</image> 
	<item>
		<title>Sentiment Analysis with Transformers</title>
		<link>https://dcn.nat.fau.eu/ndw25-sentiment-analysis-with-transformers/</link>
		
		<dc:creator><![CDATA[darlis.dcn]]></dc:creator>
		<pubDate>Fri, 14 Nov 2025 12:00:05 +0000</pubDate>
				<category><![CDATA[Hub]]></category>
		<category><![CDATA[Hub Albert Alcalde]]></category>
		<category><![CDATA[Math]]></category>
		<category><![CDATA[Math Albert Alcalde]]></category>
		<category><![CDATA[Math Giovanni Fantuzzi]]></category>
		<guid isPermaLink="false">https://dcn.nat.fau.eu/?p=32036</guid>

					<description><![CDATA[Sentiment Analysis with Transformers This post includes an app SentimentAnalysisTransformersApp created for a public outreach activity organized by the Chair for Dynamics, Control, Machine Learning and Numerics – Alexander von Humboldt Professorship (FAU DCN-AvH) during the Lange Nacht der Wissenschaften 2025 (Long Night Sciences 2025). Live demo https://albertalcalde.github.io/SentimentAnalysisTransformersApp/ Overview This interactive app lets you type [&#8230;]]]></description>
		
		
		
			</item>
		<item>
		<title>Clustering in pure-attention hardmax transformers and its role in sentiment analysis</title>
		<link>https://dcn.nat.fau.eu/clustering-in-pure-attention-hardmax-transformers-and-its-role-in-sentiment-analysis/</link>
		
		<dc:creator><![CDATA[darlis.dcn]]></dc:creator>
		<pubDate>Wed, 03 Jul 2024 01:46:03 +0000</pubDate>
				<category><![CDATA[Hub]]></category>
		<category><![CDATA[Hub Albert Alcalde]]></category>
		<category><![CDATA[Math]]></category>
		<category><![CDATA[Math Albert Alcalde]]></category>
		<guid isPermaLink="false">https://dcn.nat.fau.eu/?p=29583</guid>

					<description><![CDATA[Clustering in pure-attention hardmax transformers and its role in sentiment analysis This post provides an overview of the results in the paper Clustering in Pure-Attention Hardmax Transformers and its Role in Sentiment Analysis by Albert Alcalde, Giovanni Fantuzzi, and Enrique Zuazua [1]. Codes used to reproduce the simulations can be found at the repository: https://github.com/DCN-FAU-AvH/clustering-hardmax-transformers [&#8230;]]]></description>
		
		
		
			</item>
		<item>
		<title>PINNs Introductory Code for the Heat Equation</title>
		<link>https://dcn.nat.fau.eu/pinns-introductory-code-for-the-heat-equation/</link>
		
		<dc:creator><![CDATA[darlis.dcn]]></dc:creator>
		<pubDate>Fri, 01 Dec 2023 14:54:19 +0000</pubDate>
				<category><![CDATA[Hub]]></category>
		<category><![CDATA[Hub Martín Hernández]]></category>
		<category><![CDATA[Hub Ziqi Wang]]></category>
		<category><![CDATA[Math]]></category>
		<category><![CDATA[Math Martin Hernandez]]></category>
		<category><![CDATA[Math Ziqi Wang]]></category>
		<category><![CDATA[controlling physical systems]]></category>
		<category><![CDATA[Reinforcement learning]]></category>
		<category><![CDATA[RL]]></category>
		<guid isPermaLink="false">https://dcn.nat.fau.eu/?p=27768</guid>

					<description><![CDATA[PINNs Introductory Code for the Heat Equation This repository provides some basic insights on Physics Informed Neural Networks (PINNs) and their implementation. PINNs are numerical methods based on the universal approximation capacity of neural networks, aiming to approximate solutions of partial differential equations. Recently, extensive focus has been on approximating solutions of various equations, leading [&#8230;]]]></description>
		
		
		<enclosure url="https://dcn.nat.fau.eu/wp-content/uploads/FAUDCNAvHpost_zWang_mHernandez_trainingSolConv.mp4" length="355115" type="video/mp4" />

			</item>
		<item>
		<title>Combined convection and diffusion in a network. A numerical analysis</title>
		<link>https://dcn.nat.fau.eu/combined-convection-and-diffusion-in-a-network-a-numerical-analysis/</link>
		
		<dc:creator><![CDATA[darlis.dcn]]></dc:creator>
		<pubDate>Fri, 04 Aug 2023 09:13:30 +0000</pubDate>
				<category><![CDATA[Hub]]></category>
		<category><![CDATA[Hub Dragos Manea]]></category>
		<category><![CDATA[Math]]></category>
		<category><![CDATA[Math Dragos Manea]]></category>
		<guid isPermaLink="false">https://dcn.nat.fau.eu/?p=27049</guid>

					<description><![CDATA[Combined convection and diffusion in a network. A numerical analysis. The problem: a contaminant in a network of water pipes Imagine that there is a network of pipes full of water. The water is flowing from some source nodes (say, some water plants) to some destination nodes (say, people’s homes). A contaminant is present in [&#8230;]]]></description>
		
		
		
			</item>
		<item>
		<title>The ADMM-PINNs Algorithmic Framework for Nonsmooth PDE-Constrained Optimization: A Deep Learning Approach</title>
		<link>https://dcn.nat.fau.eu/the-admm-pinns-algorithmic-framework-for-nonsmooth-pde-constrained-optimization-a-deep-learning-approach/</link>
		
		<dc:creator><![CDATA[darlis.dcn]]></dc:creator>
		<pubDate>Wed, 12 Jul 2023 09:00:42 +0000</pubDate>
				<category><![CDATA[Hub]]></category>
		<category><![CDATA[Hub Yongcun Song]]></category>
		<category><![CDATA[Math]]></category>
		<category><![CDATA[Math Yongcun Song]]></category>
		<category><![CDATA[controlling physical systems]]></category>
		<category><![CDATA[Reinforcement learning]]></category>
		<category><![CDATA[RL]]></category>
		<guid isPermaLink="false">https://dcn.nat.fau.eu/?p=26844</guid>

					<description><![CDATA[The ADMM-PINNs Algorithmic Framework for Nonsmooth PDE-Constrained Optimization: A Deep Learning Approach Motivation This post shows the source code from the paper &#8220;The ADMM-PINNs Algorithmic Framework for Nonsmooth PDE-Constrained Optimization: A Deep Learning Approach&#8221;. (See reference below) We study the combination of the alternating direction method of multipliers (ADMM) with physics-informed neural networks (PINNs) for [&#8230;]]]></description>
		
		
		
			</item>
		<item>
		<title>Reinforcement learning as a new perspective into controlling physical systems</title>
		<link>https://dcn.nat.fau.eu/reinforcement-learning-as-a-new-perspective-into-controlling-physical-systems/</link>
		
		<dc:creator><![CDATA[darlis.dcn]]></dc:creator>
		<pubDate>Mon, 03 Jul 2023 03:43:26 +0000</pubDate>
				<category><![CDATA[Hub]]></category>
		<category><![CDATA[Hub Theïlo Terrise]]></category>
		<category><![CDATA[Math]]></category>
		<category><![CDATA[Math Theïlo Terrise]]></category>
		<category><![CDATA[controlling physical systems]]></category>
		<category><![CDATA[Reinforcement learning]]></category>
		<category><![CDATA[RL]]></category>
		<guid isPermaLink="false">https://dcn.nat.fau.eu/?p=26794</guid>

					<description><![CDATA[Reinforcement learning as a new perspective into controlling physical systems Introduction Optimal control addresses the problem of bringing a system from an initial state to a target state, like a satellite that we want to send into orbit using the least possible amount of fuel. Since the last century, mathematics has helped develop powerful numerical [&#8230;]]]></description>
		
		
		
			</item>
		<item>
		<title>Federated Learning: Protect your data and privacy</title>
		<link>https://dcn.nat.fau.eu/federated-learning-protect-your-data-and-privacy/</link>
		
		<dc:creator><![CDATA[darlis.dcn]]></dc:creator>
		<pubDate>Tue, 20 Dec 2022 06:50:47 +0000</pubDate>
				<category><![CDATA[Hub]]></category>
		<category><![CDATA[Hub Ziqi Wang]]></category>
		<category><![CDATA[Math]]></category>
		<category><![CDATA[Math Ziqi Wang]]></category>
		<guid isPermaLink="false">https://dcn.nat.fau.eu/?p=25318</guid>

					<description><![CDATA[Federated Learning: Protect your data and privacy Code: A basic PyTorch implementation of the FedAvg algorithm (GitHub) Federated Learning is becoming an increasingly popular topic in machine learning. But what is it, and why do we need it? To explain what the excitement is all about, this post outlines the basics of Federated Learning and [&#8230;]]]></description>
		
		
		
			</item>
		<item>
		<title>Approximating the 1D wave equation using Physics Informed Neural Networks (PINNs)</title>
		<link>https://dcn.nat.fau.eu/approximating-the-1d-wave-equation-using-physics-informed-neural-networks-pinns/</link>
		
		<dc:creator><![CDATA[darlis.dcn]]></dc:creator>
		<pubDate>Fri, 30 Sep 2022 10:59:13 +0000</pubDate>
				<category><![CDATA[All]]></category>
		<category><![CDATA[Hub]]></category>
		<category><![CDATA[Hub Dania Sana]]></category>
		<category><![CDATA[Math]]></category>
		<category><![CDATA[Math Dania Sana]]></category>
		<category><![CDATA[boundary controllability]]></category>
		<category><![CDATA[Machine Learning]]></category>
		<category><![CDATA[parameter identification]]></category>
		<category><![CDATA[physics-informed neural networks]]></category>
		<category><![CDATA[wave equation]]></category>
		<guid isPermaLink="false">https://dcn.nat.fau.eu/?p=22800</guid>

					<description><![CDATA[Approximating the 1D wave equation using Physics Informed Neural Networks (PINNs) &#160; Introduction Accurate and fast predictions of numerical solutions are of significant interest in many areas of science and industry. On one hand, most theoretical methods used in the industry are the result of deriving differential equations that are based on conservation laws, physical [&#8230;]]]></description>
		
		
		
			</item>
		<item>
		<title>Training of neural ODEs using pyTorch</title>
		<link>https://dcn.nat.fau.eu/training-of-neural-odes-using-pytorch/</link>
		
		<dc:creator><![CDATA[darlis.dcn]]></dc:creator>
		<pubDate>Tue, 13 Sep 2022 14:11:31 +0000</pubDate>
				<category><![CDATA[Hub]]></category>
		<category><![CDATA[Hub Tobias Wöhrer]]></category>
		<guid isPermaLink="false">https://dcn.nat.fau.eu/?p=24809</guid>

					<description><![CDATA[Start with tutorials to get familiar with the code Tutorial 1: Train a neural ODE based network on point cloud data set and generating a gif of the resulting time evolution of the neural ODE Code: Code is based on GitHub: borjanG : 2021-dynamical-systems that uses the torchdiffeq package GitHub : rtqichen: torchdiffeq &#160; Code: [&#8230;]]]></description>
		
		
		
			</item>
		<item>
		<title>Gas networks at stationary states: Analysis, software and visualization</title>
		<link>https://dcn.nat.fau.eu/derivation-of-the-pressure-function/</link>
		
		<dc:creator><![CDATA[darlis.dcn]]></dc:creator>
		<pubDate>Fri, 05 Aug 2022 11:13:39 +0000</pubDate>
				<category><![CDATA[All]]></category>
		<category><![CDATA[Hub]]></category>
		<category><![CDATA[Hub Veronika Riedl]]></category>
		<category><![CDATA[Math]]></category>
		<category><![CDATA[Math Veronika Riedl]]></category>
		<guid isPermaLink="false">https://dcn.nat.fau.eu/?p=21384</guid>

					<description><![CDATA[Gas networks at stationary states: Analysis, software and visualization Code: Files to run: nocircle.m, onecircle.m or twocircles.m &#160; 1 Introduction This post presents the results of my Bachelor thesis about the modeling and implementation of gas networks at stationary states. Using the isothermal Euler equations to describe the gas flow through a single pipe, algebraic [&#8230;]]]></description>
		
		
		
			</item>
	</channel>
</rss>
