🚨 Open #NeuroAI position for a PhD student
Jointly at MPI for Software Systems & UoT
(hosted by me & @neurodidact)
Focus: reveal key *mechanisms* of language in 🧠 by integrating ML & physiological theories
Apply by Jan 31: email CV + statement of interest to both hosts
Can machine learning uncover the multivariate neural signature of major depressive disorder in individual patients? This large-scale study including 1,801 patients and controls finds no robust multivariate depression markers. https://t.co/h0VprWgKBJ
Nils Winter, @TheRealTimHahn1 et al. are at it again:
In a case (945 MDD) control (856 healthy) study + replication sample (n=1198), #MachineLearning models using (f)MRI data were unable to recover biomarker for depression, w mean classification accuracies between 48% - 62.0%.
🔥 Exciting news for the #neuroimaging community! Introducing #torchreg a lightweight #PyTorch library for 2D and 3D image registration📸
🔗 GitHub: codingfisch/torchreg
Install via
```
pip install torchreg
```
for fast image registration on your GPU🚀
@Olvekr That would be fascinating. A whole back I did a short Internet research and couldn’t find a whole lot of German sources. I do know however that his Norwegian Wikipedia page is much more thorough than the German for example. I’d love to read more about him!
Join us at @OHBM for an immersive course on Whole Brain Modelling! 🧠💻 Experience a hybrid approach with theoretical lectures and hands-on implementation in Jupyter Colab. Check out our amazing Team:
https://t.co/2XD7YJXOuD
#OHBM#BrainModelling#Model4Life#ScienceTwitter
Behold! A complete list of how much OpenAI likes various groups based on how often questions are called "hateful". It's basically a list of how popular such groups are in the collective leftist worldview. In other words, protected classes.
https://t.co/92K9h5UW5h
Very happy to share the latest paper from @wwu_mmll. We formally link Postictal Suppression Index to brain #controllability. Then, we show that we can use this link to predict response to #electroconvulsivetherapy BEFORE it starts from a #DTI brain scan.
https://t.co/zex9mfinLQ
The idea that mostly-random search + tons of time + a simple loss function (survival) is how human were created is, in my view, the most stunning insight a person has ever had.
I am worried and scared by vendors in the #radiologyAI space who don't understand the radiology interpretation process, and the high consequences of being not only inaccurate but incomplete. A 🧵
@TheRealTimHahn1 showing convincingly how similar patients with major depressive disorders and healthy controls are in regard to many biomarkers (imaging, genetics, etc.). Where do we go from here?
https://t.co/dOmH0hi1ds