🧪 ⚛️ Just appeared in Physica A: The statistical physics of learning in under- and over-parameterized layered neural networks with Otavio Citton and F. Richert doi.org/10.1016/j.ph...
Redirecting
doi.org
Michael Biehl
@michaelbiehl.bsky.social
Physicist by training and by heart, now machine learner in Groningen / NL. Visit www.cs.rug.nl/~biehl for more information, publications, etc. The Shallow and the Deep (open access lecture notes): https://books.ugp.rug.nl/index.php/ugp/catalog/book/130
Another publication emerging from the collaboration of Intelligent Systems/Bernoulli Institute @rug.nl and Movement Disorder research @umcgroningen.bsky.social open access at @sciencedirect.bsky.social www.sciencedirect.com/science/arti...
Enhanced broad-band intermuscular coherence in myoclonus: a targeted characterization study
To describe the occurrence of enhanced broad-band intermuscular coherence (eIMC) in cortical myoclonus (CM) and to examine whether this pattern reflec…
sciencedirect.com
A 𝗧𝗲𝗻𝘂𝗿𝗲 𝗧𝗿𝗮𝗰𝗸 𝗔𝘀𝘀𝗶𝘀𝘁𝗮𝗻𝘁 𝗣𝗿𝗼𝗳𝗲𝘀𝘀𝗼𝗿 𝗽𝗼𝘀𝗶𝘁𝗶𝗼𝗻 is available at the Bernoulli Institute of the @rug.nl. Looking for a creative researcher working in one or more of the following areas: machine learning, visualization or computer graphics, distributed systems Details: werkenbij.rug.nl/vacature/ass...
linkedin.com
🧪 Our article "Machine learning based EMG analysis of intermuscular coherence and cumulant density in tremor and myoclonus" is now available (proof) A collaboration of Movement Disorders Groningen @umcgroningen.bsky.social and the Bernoulli Institute @rug.nl www.sciencedirect.com/science/arti...
Machine learning based EMG analysis of intermuscular coherence and cumulant density in tremor and myoclonus
Clinical distinction of essential tremor (ET) and cortical myoclonus (CM) remains challenging due to overlapping symptoms. This study aims to identify…
sciencedirect.com
Ich bin schon so gespannt, wie man uns dann nach dem AI-Crash erklärt, dass die großen AI-Konzerne zwar jetzt alle zahlungsunfähig sind, aber AI halt nun mal zur unverzichtbaren Infrastruktur geworden ist, weshalb ein Bailout mit Steuergeld unvermeidlich ist.
Liebe Kolleginnen und Kollegen: Der Irankrieg hat nicht „die Energiepreise“ erhöht, sondern die für Öl und Gas. Es werden nicht „die Autofahrer entlastet“, es werden Kosten für den Teil der Bevölkerung reduziert, der einen Verbrenner fährt. Auf Kosten aller anderen.
Es ist an der Zeit, dass die Homöopathie nun endlich raus fliegt aus der Erstattung der gesetzlichen Krankenkassen. Weder als Regelleistung für Kinder noch als freiwillige Satzungsleistung oder als Selektivvertrag darf es einen Platz in einem auf dem Solidaritätsprinzip beruhenden System haben!
The importance of lunch breaks cannot be overrated! This work emerged from a discussion at ESANN2024, was presented at ESANN2025 and extended for Neurocomputing. With @hsmw.bsky.social colleagues, @bernoulliinstitute.bsky.social : S Lövdal, EL van den Brandhof and M Biehl doi.org/10.1016/j.ne...
Redirecting
doi.org
📢 We’re now accepting applications for the 2026 School on Analytical Connectionism dedicated this year to Language Acquisition. 📍 Gothenburg, Sweden 🗓️ August 17–28, 2026 ☠️ Apply by April 17! 🔗 analytical-connectionism.net/school/2026/ 👇 Meet the experts joining us this summer!
🧪 Publication in @ebiomedicine.bsky.social, project led by @wiebkearlt.bsky.social @mrc-lms.bsky.social & A Prete @unibirmingham.bsky.social with important contributions from @rug.nl theses by @ariadnaalbors.bsky.social , E van den Brandhof, Y Zhang & L Visser www.sciencedirect.com/science/arti...
Endocrine and metabolic determinants of cardiometabolic risk in mild autonomous cortisol secretion
Benign adrenal tumours, found in 1–7% of adults, can be non-functioning (NFAT) or show mild autonomous cortisol secretion (MACS), i.e., biochemical co…
sciencedirect.com
Dieses Thema liegt mir am Herzen. Bitte hier unterzeichnen: weact.campact.de/petitions/ha...
Haltung zeigen: WM-Teilnahme absagen – DFB-Team zurückziehen!
Als vierfacher Fußball-Weltmeister ist unsere Nationalmannschaft Vertreter eines weltoffenen und toleranten, demokratischen und friedlichen Deutschlands. Sie darf nicht Statist für Donald Trump und ei...
weact.campact.de
Our paper "Iterated relevance matrix analysis for improved classification and robustness in prototype-based learning schemes" appears in Neurocomputing. This work with first authors Sofie Lövdal and Elina van den Brandhof is available at www.sciencedirect.com/science/arti... 🧪 #machinelearning
Iterated relevance matrix analysis for improved classification and robustness in prototype-based learning schemes
Generalized Matrix Learning Vector Quantization (GMLVQ) is an inherently interpretable classifier, but the learned distance measure may converge into …
sciencedirect.com
Sofie Lövdal presenting our joint work with Elina van den Brandhof on Iterated Relevance Matrix Analysis (IRMA) at the #AliceAndEve event, Bernoulli Institute, University of Groningen,11/01/25 See preprint version: papers.ssrn.com/sol3/papers....
Iterated Relevance Matrix Analysis (IRMA) for improved robustness of protoytype based systems A preprint version of a paper with Sofie Lövdal and Elina van den Brandhof is available at SSRN: papers.ssrn.com/sol3/papers.... 🧪 #machinelearning #computerscience
Iterated Relevance Matrix Analysis for improved robustness in prototype-based learning schemes
Prototype-based classifiers such as Generalized Matrix Learning Vector Quantization (GMLVQ) are inherently interpretable, but training may converge into differe
papers.ssrn.com
+++ Eilmeldung +++ Medizin-Nobelpreis geht an Donald Trump www.der-postillon.com/2025/10/medi...
+++ Eilmeldung +++ Medizin-Nobelpreis geht an Donald Trump
Stockholm, Washington (dpo) - Der Nobelpreis für Medizin geht in diesem Jahr in die USA: Für den Nachweis des Zusammenhangs zwischen der Einnahme von
der-postillon.com
The perspective paper Aligning generalization between humans and machines emerged from the excellent Dagstuhl Seminar “Generalization by People and Machines”, which took place in May 2024. A complementary "view only" version is provided by Nature Machine Intelligence: rdcu.be/eH1AJ
Aligning generalization between humans and machines
Nature Machine Intelligence - Ilievski et al. examine differences and similarities in the various ways human and AI systems generalize. The insights are important for effectively supporting...
rdcu.be
Seriously. Avoid the term "AI" as much as you can. Don't fall for the hype and don't fuel it. Here's a brief rant that I presented at the Mittweida Workshop on Computational Intelligence 2025 (presentation slightly messed up by slideshare and adds the stupid ads) www.slideshare.net/slideshow/it...
It AI'nt what you think - let's drop the term
A rant, arguing that we should avoid the term "AI" in acadamia and everywhere else. - View online for free
slideshare.net
Proud to be one of the 25 (in-) credible authors 😀
Martin Mundt@martinmundt.bsky.social · 12mo ago🎉"Aligning generalization between humans and machines" (w/ 25 incredible authors) is out now in #Nature Machine Intelligence: www.nature.com/articles/s42... In short, we identified interdisciplinary commonalities & differences with respect to notions of, methods for, & evaluation of generalization
Fantastic output of the great Dagstuhl Seminar “Generalization by People and Machines”, which took place in May 2024. Thanks for having me as a participant and co-author! www.nature.com/articles/s42...
Aligning generalization between humans and machines - Nature Machine Intelligence
Ilievski et al. examine differences and similarities in the various ways human and AI systems generalize. The insights are important for effectively supporting alignment in human–AI teams.
nature.com
Hermite polynomials facilitating on-line learning analysis of layered neural networks with arbitrary activation function by O. Citton, F. Richert , M. Biehl, and M. Straat Neurocomputing Volume 655, 28 November 2025, 131328 Published version available online www.sciencedirect.com/science/arti...
Hermite polynomials facilitating on-line learning analysis of layered neural networks with arbitrary activation function
Following the standard statistical mechanics methods we analyze the training by online stochastic gradient descent of two-layer neural networks in a s…
sciencedirect.com
If AI can’t explain its decisions, how can we trust it? Explainability isn’t a luxury — it’s a foundation for transparency, accountability, and human oversight. XAI isn’t optional. It’s essential. #XAI #AIUnpacked #ExplainableAI #ResponsibleAI
🧪 Open Access publication on explainable #MachineLearning in movement disorders, a collaboration of the Expertise Center at @umcgroningen.bsky.social and Intelligent Systems at the Bernoulli Institue @rug.nl www.sciencedirect.com/science/arti...
Explainable machine learning for movement disorders - Classification of tremor and myoclonus
Treatment for essential tremor (ET) and cortical myoclonus (CM) differs. As their clinical distinction can be difficult, with large inter- and intra-o…
sciencedirect.com
Our work on Explainable Machine Learning for Movement Disorders a collaboration of the Expertise Center Movement Disorders at @umcgroningen.bsky.social and the Intelligent Systems group at the Bernoulli Institue @rug.nl is now available online (open access): www.sciencedirect.com/science/arti...
Explainable machine learning for movement disorders - Classification of tremor and myoclonus
Treatment for essential tremor (ET) and cortical myoclonus (CM) differs. As their clinical distinction can be difficult, with large inter- and intra-o…
sciencedirect.com
Imho it is time to break away from the AI hype and get serious again. I'm afraid it's too late to reclaim the (old) term Artificial Intelligence for reasonable use. Maybe we should give in and leave the term to the LLM, genAI and AGI crowd, to "big tech" and the media. #machinelearning #AI #hype
1. I study how science works as a collective endeavor to make sense of the physical world. I also study how misinformation about science spreads and affects society. There are fewer examples more poignant than a Minnesota bill that would criminalize mRNA vaccines as weapons of mass destruction.
Chris Ingraham@cingraham.bsky.social · last yr.This morning Minnesota Republicans introduced a bill banning mRNA vaccines and labeling them "weapons of mass destruction." It would make manufacturing, possessing or administering them a crime punishable by up to 20 years in prison. www.revisor.mn.gov/bills/bill.p...
Three contributions to the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2025) are available online: doi.org/10.14428/esa... doi.org/10.14428/esa... doi.org/10.14428/esa... www.esann.org
Home | ESANN 2025
esann.org
Mr. Trump, this statute at the National Museum of African American History and Culture does not "undermine the remarkable achievements of the United States". It does not "fosters a sense of national shame." It does not "advance a corrosive ideology." It is literally what might redeem the USA.
