| Homepage | https://www.mlmia-unitue.de/authors/christian-baumgartner/ |
Beyond the L2L challenge, our aim is to provide a valuable data and code resource for benchmarking algorithms on a wide range of medical tasks with standardised data splits.
We want to make CD-FSL accessible to MICCAI folks, and medical imaging accessible to ML folks! 🤖👩⚕️
We are delighted to announce the #MICCAI Learn2Learn challenge! 🎉
Download and explore our dataset of 28 unique tasks derived from 17 medical image datasets & create algorithms that learn new tasks with minimal annotated examples!
All information here: http://l2l-challenge.org
Workshops, lectures, conferences - acedemics travel a lot. But how do you get to scientific events #climatefriendly? By bike, by train or not travelling at all?
Check out our latest blog article with a video interview!
#opinionpiece #businesstravel
@unituebingen @CellTypist @sethaxen @chrigi
https://www.machinelearningforscience.de/en/how-to-make-business-trips-more-climate-friendly/
A meeting in Vienna, a lecture in Boston, a conference in London – academic events such as these are a part of researchers’ everyday working lives. In the following, some of our researchers and scholars share their experiences on the road and reveal their motivation to approach business trips in a more climate-friendly way.
Taking a closer look at this paper, I really dislike it.
https://www.nature.com/articles/s41586-022-05543-x
It's clear that newer papers *must* have a lower “disruption” score than older ones under a null model — they even confirm this in the supplemental material with a randomization test. It's an artifact of their definition.
When comparing with the null model they compute only the z-score, getting values at most 4 or so. It's also besides the point — as usual, small meaningless deviations from the null model can be statistically “significant.” Effect size ≠ statistical significance.
Finally, according to their definition, review papers would be “disruptive” because they funnel a bunch of citations. And a paper that does not cite anyone but is universally cited would not be “disruptive”. 🤷
If you installed PyTorch-nightly on Linux between Dec. 25 and Dec. 30, uninstall it and torchtriton immediately and use the latest nightly binaries.
Read the security advisory here: https://pytorch.org/blog/compromised-nightly-dependency/
A front page article on the Washington Post telling people how to get started with Mastodon?
That’s a big deal.
https://www.washingtonpost.com/technology/2022/12/17/how-to-join-mastodon/
ml4science
Tiago Peixoto
PyTorch
Duane O'Brien