iiinova — where your digital self keeps evolving

🔣 Input: your positive or negative sentiment. 📊 Output: A 2D visualization that shows how a Transformer model processes and transforms your words layer by layer. See more 🔗 dcn.nat.fau.eu/ndw25-sentim... #FAU #movingKnowledge #NdW25 #FAUMoD #DTNModConFlex #EUhorizon

000

This app makes those hidden transformations visible: as the layers advance, you can watch how your words become points on a plane, clustering and shifting as the model “understands” your sentence: . . .

100

👉🏻Why it’s Interesting Transformer models understand text by gradually updating internal word representations through multiple layers. Each layer refines meaning and relationships, but that process is normally invisible to us. . . .

100

This post includes an app SentimentAnalysisTransformersApp created for a public outreach activity organized by our Chair during the Lange Nacht der Wissenschaften 2025 (Long Night Sciences 2025). . . .

100

The authors of this post are supported by the @modconflex.bsky.social funded by the MSCA, European Union (Grant ID 10107355) See more 🔗 dcn.nat.fau.eu/ndw25-sentim...

100

FAU DCN-AvH @faudcnavh.bsky.social · 14/10/2025

NEW #mathPost at 🚀 #FAUDCNAvH @fau.de Sentiment Analysis with Transformers ▪️Albert Alcalde, PhD student at @faudcnavh.bsky.social Dynamics, Control, Machine Learning and Numerics - AvH ▪️Giovanni Fantuzzi, W1 Professor | Senior Scientist #FAU @faumod.bsky.social 🔗 dcn.nat.fau.eu/ndw25-sentim... ...

152

"How do #AI models understand emotions in text? In this interactive experiment, you can type your own sentences and see how a transformer-based AI analyzes sentiment in real time. (...)" SEE MORE 🔗 go.fau.de/1cbb- #FAUDCNAvH #FAUMoD #longNightSciences #Sciences #AImodels #transformer

000

FAU DCN-AvH @faudcnavh.bsky.social · 14/10/2025

NEW 📢 #NdW25 Lange Nacht der Wissenschaften (Long Night Sciences) 📍 @fau.de Exhibition "Sentimentanalyse mit Transformern in Aktion" 🔸 Giovanni Fantuzzi @faumod.bsky.social 🔸 Albert Alcalde @faudcnavh.bsky.social SEE MORE 🔗 go.fau.de/1cbb- #FAU #movingKnowledge

FAU MoD @faumod.bsky.social · 11/10/2025

Reposted by FAU DCN-AvH

You’re invited 🚀 Oct. 13, 2025 #FAUMoD lecture: Disruption in science and engineering happens at scale Prof. Johannes Brandstetter, JKU / EmmiAI On-site / Online 📍 @fau.de See more 🔗 go.fau.de/1c-bb

131

Reposted by FAU DCN-AvH

FAU Erlangen-Nbg @fau.de · 18/08/2025

Im aktuellen Shanghai-Ranking 2025 hat sich die FAU abermals verbessert. Zum Beispiel erobert sie im nationalen Vergleich Rang 17. In der Kategorie „Akademische Pro-Kopf-Leistung einer Einrichtung“ landet sie unter den hundert besten Universitäten weltweit. go.fau.de/1ca-a

fau.de

Shanghai-Ranking 2025: FAU verbessert sich national und international

Im aktuellen Shanghai-Ranking 2025 hat sich die FAU abermals verbessert: Beim internationalen Vergleich kann die Universität vier Plätze gut machen und landet auf Platz 242.

0132

FAU DCN-AvH @faudcnavh.bsky.social · 24/07/2025

The workshop aims to advance research at the intersection of control theory, scientific computing, partial differential equations (PDEs), and machine learning. SEE MORE 🔗 go.fau.de/1c-ec

FAU DCN-AvH @faudcnavh.bsky.social · 24/07/2025

000

Starting 🔜 🤩July 25 – 27, 2025 Workshop on Recent Trends in Applied Mathematics and Machine Learning #FAUMoD and #FAUDCNAVH at @fau.de in collaboration with #JLU Online📍Onsite: Jilin University Watch the spot 🎬 youtube.com/shorts/dXNZT... @faumod.bsky.social

youtube.com

Recent Trends in Applied Mathematics and Machine Learning #FAU #JLU #onsite #online #workshop

YouTube video by FAU MoD, Research Center for Mathematics of Data

July 21-23, 2025: Course by Prof. Zuazua @Unifau PDEs meet Machine Learning #maths #pde #research

Just few hours away 🤩 July 21-23, 2025 Short course 🔸 Prof. Enrique Zuazua Iriondo @fau.de : "PDEs Meet Machine Learning: Integrating Numerics, Control, and Machine Learning" Online: Zoom 📍 On-site host: Jilin University 🔗 go.fau.de/1c-ba #FAU #movingKnowledge 🎬 YouTube youtube.com/shorts/0yL5b...

youtube.com

YouTube video by FAU Chair Dynamics, Control, Machine Learning...

032

We examine the intrinsic connections between representation, optimization, and control theory—rooted in cybernetics (from Ampère to Wiener) and historically motivated by the quest to design intelligent machines. (...)"

000

(...) This course explores these questions through an interdisciplinary lens, bridging PDE theory, control, and ML. #FAU #movingKnowledge

100

About this course ▪️Can ML enhance PDE techniques without sacrificing mathematical rigor? ▪️ Can we develop hybrid computational frameworks that leverage data-driven approaches while maintaining the reliability of traditional methods?

100

in terms of moment order, terminal time, and measurement errors. In addition, we develop efficient numerical discretization schemes and demonstrate significant stability improvements of our approach through comprehensive numerical experiments." 🔗 cris.fau.de/publications... #FAU #FAUMoD #research

000

transforming the problem into a more stable inverse moment formulation. Compared to existing methods, our moment-based approach reduces exponential error growth to polynomial growth with respect to the terminal time. We provide explicit error estimates on the recovered initial distributions ....

100

"We address the initial source identification problem for the heat equation, a notably ill-posed inverse problem characterized by exponential instability. Departing from classical Tikhonov regularization, we propose a novel approach based on moment analysis of the heat flow, (...)

100

darlis ツ @darlisbt.bsky.social · 07/07/2025

NEW 📣publication at our #FAUCRIS: Moments, time-inversion and source identification for the heat equation 🔸 Kang Liu, Université Bourgogne Europe 🔸 Enrique Zuazua Iriondo, @fau.de @faumod.bsky.social 🔗 cris.fau.de/publications... #FAU #FAUDCNAvH #FAUMoD #research #movingKnowledge #mathematik

121

Reposted by FAU DCN-AvH

Join us TODAY! On-site: @fau.de 📍 Online Live-streaming: www.fau.tv/fau-mod-live...

031

Reposted by FAU DCN-AvH

FAU MoD @faumod.bsky.social · 07/07/2025

TODAY📢 #FAUMoD lecture Mon. July 7, 2025 📌 On-site / Online Exemplary applications of machine learning and optimization in quantum chemistry 🔹Prof. Dr. Andreas Görling @fau.de See more: go.fau.de/1bidf @faumod.bsky.social #FAU #FAUMoD #movingKnowledge #erlangen #online

FAU MoD Lecture @07.07.2025
Exemplary applications of machine learning and optimization in quantum chemistry
www.mod.fau.eu

On-site / Online

031

Reposted by FAU DCN-AvH

FAU MoD @faumod.bsky.social · 02/06/2025

Tomorrow #FAUMoD lecture at @fau.de Tue. June 3, 2025 📌On-site/Online Optimization-based control for large-scale and complex systems: When and why does it work? 🔹Prof. Lars Grüne @unibayreuth.bsky.social SEE more: go.fau.de/1bddc

142

FAU DCN-AvH @faudcnavh.bsky.social · 29/04/2025

Organizing Committee • Darlis Bracho Tudares @darlisbt.bsky.social FAU Erlangen-Nürnberg #FAU • Nicola De Nitti #Unipi • Lorenzo Liverani @faudcnavh.bsky.social Thanks to the support @humboldt-foundation.de @faudcnavh.bsky.social #AFOSR #Poliba

000

FAU DCN-AvH @faudcnavh.bsky.social · 29/04/2025

Scientific Committee • Giuseppe M. Coclite. Politecnico di Bari • Enrique Zuazua Iriondo. @faumod.bsky.social Research Center for Mathematics of Data at @fau.de

120

FAU DCN-AvH @faudcnavh.bsky.social · 29/04/2025

#MLPDES25 Day 2 🔛 Onsite📍@fau.de Live-streaming🔗 go.fau.de/1begh 🚀Our speakers gabrielpeyre.bsky.social @cnrs.fr ENS-PSL G. Orlando #Poliba A. Coclite #Poliba B. Geshkovski #Inria @sorbonne-universite.fr D. Ruiz-Balet @univdauphine.bsky.social A. Porretta #UniRoma2 Y. Zhang #SJTU G. Leugering #FAU

122

Reposted by FAU DCN-AvH

darlis ツ @darlisbt.bsky.social · 28/04/2025

Our #MLPDES25 workshop at @fau.de 🤩is here!! Machine Learning & PDEs Workshop Join us on-site (#FAU Erlangen) or online: On-site📍@faumod.bsky.social Live📽️ www.fau.tv/fau-mod-live... A huge THANK YOU to our amazing speakers, sponsors & committees for this amazing event 🙌🏻 @faudcnavh.bsky.social

FAU DCN-AvH @faudcnavh.bsky.social · 28/03/2025

April 1, 2025 📌 15:00H Langtangen Seminar: Control & Machine Learning Prof. Enrique Zuazua @fau.de ,,We will explore the deep connections between systems control, AI, and mathematics, highlighting recent advancements in PDE+D(ata) & Digital Twin technologies." dcn.nat.fau.eu/events/langt...

000

📊What you will gain • Collaboration with experts in the field • Contact with the most innovative high-tech companies • Contributing to groundbreaking research • International Networking and growth opportunities

ERC Advanced Grant CoDeFeL project PhD positions in “Control and Machine Learning”, Erlangen (Germany)

100

🔍What we're looking for • Strong background in Applied Mathematics • Experience with Machine Learning foundations and techniques • Enthusiasm for innovative research

ERC Advanced Grant CoDeFeL project PhD positions in “Control and Machine Learning”, Erlangen (Germany)

100

We are looking for talented individuals to participate in our cutting-edge research project ERC-CoDeFeL, led by Prof. Enrique Zuazua, in Erlangen-Germany and Bilbao-Basque Country, on the interface between Mathematical Control and Machine Learning.

ERC Advanced Grant CoDeFeL project PhD positions in “Control and Machine Learning”, Erlangen (Germany)

100

🔜 Deadline: March 25, 2025 #PhD opportunity at @fau.de Join the ERC-CoDeFeL Research project! 🚀 🔗 go.fau.de/1bgd- Are you passionate about Mathematics and Machine Learning? This #call is for you!

120

... 👉🏻This discovery exposes fundamental limits in model reduction and thermal control efficiency. 👉🏻Their findings could impact engineering, climate modeling, and biomedical applications. 👉🏻The study paves the way for more realistic and effective control strategies.” 🔗 go.fau.de/1bghf

The hidden challenge in heat equation control: Slow decay of gramian eigenvalues

000

Rethinking Heat Equation Controllability:The Hidden Limitations of Slow Eigenvalue Decay “New research challenges long-held assumptions about the controllability of heat systems. Professors Lazar and Zuazua reveal that Gramian eigenvalues decay at a slower, polynomial rate rather than exponentially.

The hidden challenge in heat equation control: Slow decay of gramian eigenvalues

100

NEW article 📢 published at Advances in Engineering (AIE): "The hidden challenge in heat equation control: Slow decay of gramian eigenvalues" Prof. Enrique Zuazua @fau.de Prof. Martin Lazar, University of Dubrovnik See more 🔗 go.fau.de/1bghf #FAU #movingKnowledge #FAUDCNAvH #eigenvalues #research

The objective of this post is to present, in an accessible manner, key results related to (OCP) and to demonstrate, through simulations, the effectiveness of the mean-field approach." 🔗 go.fau.de/1bgga