michielstock.bsky.social
@michielstock.bsky.social
New paper! 🚨
Is diversity and novelty the key to making machine learning open-ended, robust, and interpretable? Our latest paper reviews how #qualitydiversity algorithms can be used in the data-to-decision pipeline.
onlinelibrary.wiley.com/share/author...
October 20, 2025 at 11:03 AM
Reposted
New paper out! @methodsinecoevol.bsky.social
We test whether optical fibres can be used to measure microclimate temperatures in the forest, and investigate what we can learn from it. 🧵👇

The full article is published Open Access: besjournals.onlinelibrary.wiley.com/doi/10.1111/...
Continuous quantification of forest microclimate temperatures in space and time using fibre‐optic technology
Most species experience microclimate temperatures, that is, variable and fine-grained thermal conditions determined by atmospheric conditions interacting with biotic and abiotic components of the ...
besjournals.onlinelibrary.wiley.com
October 14, 2025 at 6:47 AM
Reposted
The Incerto books are written in a provocative style that may not appeal to everyone. Beneath the prose, each book explores a profound concept in probability theory. I tried to strip each to its bare bones. (1/6)
June 28, 2025 at 12:10 PM
The Incerto books are written in a provocative style that may not appeal to everyone. Beneath the prose, each book explores a profound concept in probability theory. I tried to strip each to its bare bones. (1/6)
June 28, 2025 at 12:10 PM
Small blog post on how to automate model building for mechanical systems using ModelingToolkit. #julialang

michielstock.github.io/posts/2025/p...
June 18, 2025 at 7:21 PM
The KERMIT (kermit.ugent.be) research unit at @fbwugent.bsky.social focuses on holistic modeling for life sciences. In my subunit, we are particularly interested in (stochastic, differentiable, evolutionary...) computation for plants and biotechnology.
June 10, 2025 at 9:02 AM
Finally, a new blog post! The Walk on Spheres algorithm is an elegant method for solving elliptic PDEs. Minimal implementation using #julialang

michielstock.github.io/posts/2025/W...
May 27, 2025 at 2:54 PM
Submitted a project application today and feel really good about it! Research lines have really fallen into place in the last few years!
March 31, 2025 at 11:33 AM
As everyone shares AI-generated images, I'll also post something I've created. I took up watercolors to relax, and my latest one I am quite happy about!
March 28, 2025 at 6:24 PM
Reposted
Open #PhD position alert! Join @chofski.bsky.social
and me, in thinking about how we can use (in silico) evolution in synthetic biology and biodesign! repost = 🥰
docs.google.com/document/d/1...
PhD position biodesig
PhD position in computational evolution for biodesign Biological evolution has given rise to the vast diversity and complexity of the biosphere. Evolutionary computation has made great progress in cap...
docs.google.com
February 1, 2025 at 12:11 PM
Reposted
Looking for a #PhD that is at the intersection of #biodesign, #synbio, #openendedness, #evolution? Look no further. Great supervisory team too 😉
February 1, 2025 at 4:08 AM
Open #PhD position alert! Join @chofski.bsky.social
and me, in thinking about how we can use (in silico) evolution in synthetic biology and biodesign! repost = 🥰
docs.google.com/document/d/1...
PhD position biodesig
PhD position in computational evolution for biodesign Biological evolution has given rise to the vast diversity and complexity of the biosphere. Evolutionary computation has made great progress in cap...
docs.google.com
February 1, 2025 at 12:11 PM
This beautiful paper extends the bias-variance trade-off for some losses to a bias-variance-diversity trade-off for ensembles. Diversity of the predictors always reduces the risk but might lead to more variance or bias.

arxiv.org/abs/2301.03962
A Unified Theory of Diversity in Ensemble Learning
We present a theory of ensemble diversity, explaining the nature of diversity for a wide range of supervised learning scenarios. This challenge has been referred to as the holy grail of ensemble learn...
arxiv.org
January 23, 2025 at 5:02 PM
Low-key, I'm a bit depressed about having lost the Signal chat history with a new phone. I still have the history on the Desktop app, but I am afraid of relinking and losing years of memories and photos I shared with my partner.
January 21, 2025 at 3:56 PM
Proud to have finally finished the new syllabus of my modeling course. 😌 We cover the fundamentals of modeling with ODEs and probability. I hope the students will also like it in a couple of weeks.
January 21, 2025 at 3:37 PM
I recently finished Taleb's "Fooled by Randomness". Its main thesis is that a single random draw might not look random, especially after a selection process. Such processes would be vastly different if they were repeated. In a complex world, much is beyond our control.
December 30, 2024 at 10:20 AM