Michael Biehl
@michaelbiehl.bsky.social
Physicist by training, now machine learner in Groningen / NL.
Visit www.cs.rug.nl/~biehl for further information, publications, etc.
The Shallow and the Deep (open access lecture notes):
https://books.ugp.rug.nl/index.php/ugp/catalog/book/130
Visit www.cs.rug.nl/~biehl for further information, publications, etc.
The Shallow and the Deep (open access lecture notes):
https://books.ugp.rug.nl/index.php/ugp/catalog/book/130
Pinned
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
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
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
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....
See preprint version:
papers.ssrn.com/sol3/papers....
November 3, 2025 at 9:37 AM
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....
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
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
October 7, 2025 at 12:20 PM
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
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
Reposted by Michael Biehl
+++ 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
www.der-postillon.com
October 6, 2025 at 10:28 AM
+++ Eilmeldung +++ Medizin-Nobelpreis geht an Donald Trump www.der-postillon.com/2025/10/medi...
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
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
September 25, 2025 at 6:35 AM
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
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
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...
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
www.slideshare.net
September 24, 2025 at 7:13 PM
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...
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...
Proud to be one of the 25 (in-) credible authors 😀
🎉"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
In short, we identified interdisciplinary commonalities & differences with respect to notions of, methods for, & evaluation of generalization
September 20, 2025 at 10:03 AM
Proud to be one of the 25 (in-) credible authors 😀
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...
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.
www.nature.com
September 16, 2025 at 5:36 AM
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...
www.nature.com/articles/s42...
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...
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…
www.sciencedirect.com
September 10, 2025 at 5:43 AM
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...
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...
Reposted by Michael Biehl
Mass murderer.
(gift link)
(gift link)
Kennedy Withdraws U.S. Funding Pledge to International Vaccine Agency
www.nytimes.com
June 26, 2025 at 6:13 AM
Mass murderer.
(gift link)
(gift link)
Reposted by Michael Biehl
World War 3 kinda sucks, but you know, it was either this or pronouns
June 22, 2025 at 5:08 AM
World War 3 kinda sucks, but you know, it was either this or pronouns
Reposted by Michael Biehl
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
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
June 20, 2025 at 1:22 PM
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
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...
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…
www.sciencedirect.com
June 13, 2025 at 9:43 AM
🧪
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...
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...
Dear Machine Learners. I am very worried about the current #AI #hype: once people realize how un-intelligent, costly, and useless LLMs are and how questionable #genAI is, they will probably project onto serious #ML and discredit all our work. Any idea how to prevent being thrown into the same pot?
May 30, 2025 at 4:11 PM
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
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…
www.sciencedirect.com
May 15, 2025 at 7:37 PM
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
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...
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
#machinelearning #AI #hype
April 24, 2025 at 12:07 PM
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
#machinelearning #AI #hype
Reposted by Michael Biehl
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.
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.
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...
April 21, 2025 at 11:00 PM
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.
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.
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
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
www.esann.org
April 16, 2025 at 11:02 AM
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
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
Reposted by Michael Biehl
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.
It does not "fosters a sense of national shame."
It does not "advance a corrosive ideology."
It is literally what might redeem the USA.
April 1, 2025 at 6:54 AM
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.
It does not "fosters a sense of national shame."
It does not "advance a corrosive ideology."
It is literally what might redeem the USA.
Reposted by Michael Biehl
Reposted by Michael Biehl
No, Trump has destroyed America in the eyes of the world.
February 28, 2025 at 7:18 PM
No, Trump has destroyed America in the eyes of the world.
Reposted by Michael Biehl
Wir hatten uns daran gewöhnt, das Weltgeschehen,auch die Kriege, wie aus einer Theaterloge zu betrachten, anschließend nach Hause zu gehen und vor dem Schlafen gehen noch ein Glas Wein zu trinken.Der Verrat von Trump und Vance macht uns - hoffentlich - klar, dass das Theaterstück unsere Realität ist
February 28, 2025 at 11:01 PM
Wir hatten uns daran gewöhnt, das Weltgeschehen,auch die Kriege, wie aus einer Theaterloge zu betrachten, anschließend nach Hause zu gehen und vor dem Schlafen gehen noch ein Glas Wein zu trinken.Der Verrat von Trump und Vance macht uns - hoffentlich - klar, dass das Theaterstück unsere Realität ist
Reposted by Michael Biehl
Reposted by Michael Biehl
Trump: „You (Ukraine) should never have started the war.“ - Wer sagt dem mächtigsten Mann der Welt, dass Russland die Ukraine angegriffen hat und in den besetzten Gebieten schreckliche Kriegsverbrechen verübt? Möglichst bevor er Putin die Hand schüttelt.
www.cnn.com/2025/02/18/p...
www.cnn.com/2025/02/18/p...
Trump falsely claims Ukraine started war with Russia | CNN Politics
After top US and Russian officials began peace talks without Ukrainians at the negotiating table, President Donald Trump criticized Ukrainian President Volodymyr Zelensky and continued to repeat Russi...
www.cnn.com
February 19, 2025 at 9:15 AM
Trump: „You (Ukraine) should never have started the war.“ - Wer sagt dem mächtigsten Mann der Welt, dass Russland die Ukraine angegriffen hat und in den besetzten Gebieten schreckliche Kriegsverbrechen verübt? Möglichst bevor er Putin die Hand schüttelt.
www.cnn.com/2025/02/18/p...
www.cnn.com/2025/02/18/p...