@cebraAI

🦓 Consistent EmBeddings of high-dimensional Recordings using Auxiliary variables | pip install cebra

 Dev by @mwmathislab
cebra.ai
Joined September 2021
  • Tweets87
  • Following4
  • Followers1.6K
12Media
The newest edition to the #CEBRA family! Now, you can extract dynamics and the underlying putative governing equations ♾️🧠
Mackenzie Weygandt Mathis, PhD@TrackingActions
Jun 25
🧠 Can we recover the equations governing a system directly from noisy, high-dimensional observations? #DYSCO, by Paolo Muratore, is a first step: it learns latent spaces that capture the underlying dynamics & enables recovery of governing equations 📄arxiv.org/abs/2606.13260
1
2
55
7,809
Quite thrilled that our (@stes_io & I) US patent on #cebra for use to generate time-series embeddings was granted! patents.google.com/patent/US…
Mackenzie Weygandt Mathis, PhD@TrackingActions
3 May 2023
🦓 Self-supervised multimodal ML is promising the next AI breakthrough - in our new work published in @Nature, we debut @CEBRAai: for self-supervised hypothesis- and discovery-driven science. 📝 doi.org/10.1038/s41586-023-0… 💻github.com/AdaptiveMotorCont… 🦓 cebra.ai/ 🧵⬇️
1
4
41
4,463
🦓CEBRA retweeted
🦓CEBRA@cebraAI
6 Mar 2025
Ready to start with #CEBRA for your behavioral clustering, neural data, or joint-modeling? Check out our new demo notebook to help you learn the best practices and how to develop models! cebra.ai/docs/demo_notebooks… 🌈🦓 #ML4Science
14
1
44
3,720
Ready to start with #CEBRA for your behavioral clustering, neural data, or joint-modeling? Check out our new demo notebook to help you learn the best practices and how to develop models! cebra.ai/docs/demo_notebooks… 🌈🦓 #ML4Science
14
1
44
3,720
We have a new release up! Check out 0.5.0rc1!! 🔥 Important maintenance updates to keep up with dependencies, some nee features, and preparing for much more coming in the next weeks 👀… github.com/AdaptiveMotorCont… #cebra @mwmathislab

Release v0.5.0rc1 · AdaptiveMotorControlLab/CEBRA

What's Changed Fix pandas intersphinx mapping; fix test setup by @stes in #136 Implementation for discrete multisession by @introspective-swallow in #135 Update imports in pivae from keras to ...

github.com
1
3
20
2,665
🦓CEBRA retweeted
🦓CEBRA@cebraAI
16 Sep 2023
Exciting! There is a new demo notebook for how to use #CEBRA on @AllenInstitute OpenScope project data! 🎉 contributed by @LecoqJerome, now live at cebra.ai/docs/demos.html #opensourcedata 🦓🫶 #machinelearning4neuro
1
8
1
67
13,502
🦓CEBRA retweeted
🦓CEBRA@cebraAI
26 Oct 2023
In fact, this is what this very cool preprint does, cross subject decoding using CEBRA! Mind blowing decoding across even held out cohorts of patients 🤯
Julian Neumann@neumann_wj
21 Sep 2023
Replying to @neumann_wj
First, we developed and prospectively validated plug & play movement #decoders combining #connectomics with contrastive learning in @cebraAI for #ECoG signals. The video shows decoding in a prospective validation of a model that has never seen #braindata from the patient before.
4
14
5,760
Population dynamics and deep-learning analyses (@cebraAI @TrackingActions) of anterior insula single-unit recordings uncover distinct coding patterns of anxiety-provoking and safe environments, as well as tastants of positive and negative valence.
1
1
11
1,020
🥳 check out the #DeepLabCut + #CEBRA work for behavioral analysis from @shaokaiyeah et al @NatureComms nature.com/articles/s41467-0… ⬇️

SuperAnimal pretrained pose estimation models for behavioral analysis

Nature Communications - Quantifying animal behavior is crucial in various fields such as neuroscience and ecology, yet we lack data-efficient methods to perform behavioral quantification. Here, the...

nature.com
DeepLabCut 🦄@DeepLabCut
6 Oct 2024
#SfN24 update: sadly, we are not there in person, but we love to see a lot of #DeepLabCut powered science is 🥳 and we are happy to retweet it! 💕 (tag us!) 👀 But, here is what we would present 🥰🔥 DeepLabCut 3.0 release candidate is up!🔥 pip install deeplabcut==3.0.0rc5
2
11
1,395
🤩🔥
Jérôme Lecoq@LecoqJerome
28 Jun 2023
I have been reviewing the CEBRA paper in depth. What really strikes me is the multi-sessions/animal embedding. I feel like this paper is only scratching the surface of what could be done there. For starter, we could embed across species or even between models and experiments.
524
🚨Excitingly, this new paper in @NatureComms shows #CEBRA for behavioral analysis! Using SuperAnimal model for pose, we use 🦓 to do behavioral analysis — check us out if you are considering animal behavioral clustering 🚀🐭 (we are not only for neural data! 🥳)
Mackenzie Weygandt Mathis, PhD@TrackingActions
21 Jun 2024
🔥 SuperAnimal: Foundation pose models for animals, trained on over 80K images, our model(s) can be used in the lab or the wild 🐭🐆🐄 💜models are available within @DeepLabCut & @huggingface w/extensive model/datacards 📰actu.epfl.ch/news/unifying-b… 📄nature.com/articles/s41467-0…

Unifying behavioral analysis through animal foundation models

Behavioral analysis can provide a lot of information about the health status or motivations of a living being. A new technology developed at EPFL makes it possible for a single deep learning model to...

actu.epfl.ch
2
5
48
5,622
1/2 Happy to present our new findings this Thurs 16:20 at the Mathematics of Neuroscience & AI conv. neuromonster.org. We use @TrackingActions’ lab @cebraAI to probe stimulus-induced cortical embeddings by layer, cell type, in a biophysical model of cortical microcircuit.
2
1
6
1,476
Delighted to play a small part in this tour de force from @Simon_CEChang et al ! Beautiful merger of many behavioral tasks, neural recordings, @cebraAI, opto & scRNA-seq across tasks to find flexibility (and some neg. valence stability) of neural ensembles in the amygdala 💪🔥
Simon Chang@Simon_CEChang
30 Apr 2024
Check out my latest preprint with @FermaniFederica and @caina89: “Molecular and neural mechanisms of behavioural integration in the extended-amygdala”, now on biorxiv! biorxiv.org/content/10.1101/… 1/n
1
2
17
6,199
Mackenzie Mathis @TrackingActions @EPFL_en started #Cajal2024 with an intro to the study of movement. After, she presented the challenges and accomplishments of pose estimation and the latest developments of @DeepLabCut and @cebraAI. @Cajal_Training @bdxneuroschool 15/20
1
2
19
2,619
🖤🦓🥳😱 A humbling milestone: we just hit *100* citations and >17K downloads of the software since #CEBRA was published in @Nature (May 2023)! Thank you to all the users and authors out there! 🖤🦓
3
19
2,213
🦓 Self-supervised multimodal ML is promising the next AI breakthrough - in our new work published in @Nature, we debut @CEBRAai: for self-supervised hypothesis- and discovery-driven science. 📝 doi.org/10.1038/s41586-023-0… 💻github.com/AdaptiveMotorCont… 🦓 cebra.ai/ 🧵⬇️
30
267
39
975
250,793
#CEBRA🦓can be used to build a unified neural encoding model using data from many animals, and that can then be deployed on new animals for BMI-style decoding 🦾
Mackenzie Weygandt Mathis, PhD@TrackingActions
26 Oct 2023
Replying to @TrackingActions
🔥what was super exciting is the pre-trained encoder can be used to rapidly adapt to a new dataset, which doesn’t have the same # of neurons, etc, and by rapid, in this case less than 1 sec of new data! (And this is with a super simple MLP NN and kNN decoder!)
3
10
4,035
🦓CEBRA retweeted
🦓CEBRA@cebraAI
26 Oct 2023
Did you know you can use #CEBRA for adapting to new animals, or decode across animals?! ⬇️
Mackenzie Weygandt Mathis, PhD@TrackingActions
26 Oct 2023
Replying to @TrackingActions
Alright, after a bit of a break, I want to highlight more features of CEBRA! (1) you can use it across subjects, combing spikes & calcium data to build a consistent space that can be used for cross-subject decoding! 🔥
1
4
20
4,155
What a year! ✨🎊🦓 In 2023 #CEBRA was released 🎊 We are humbled & proud that it’s being used by many: 14K pip installs and 75 citations in 8 months 🙏🏼🚀 Thank you all ❤️— you make all the coding & work worth it! 💪 Onwards to 2024, with even more on the way 🦓🔥✨
Mackenzie Weygandt Mathis, PhD@TrackingActions
3 May 2023
🦓 Self-supervised multimodal ML is promising the next AI breakthrough - in our new work published in @Nature, we debut @CEBRAai: for self-supervised hypothesis- and discovery-driven science. 📝 doi.org/10.1038/s41586-023-0… 💻github.com/AdaptiveMotorCont… 🦓 cebra.ai/ 🧵⬇️
9
38
8,005
Open Science in action: The incredibly talented @MerkTimon from our @ICNeuromodulate team has made his first contribution to @TrackingActions and @stes_io @cebraAI . Check out CEBRA for human decoding: bit.ly/invasiveBCI @EPFLOpenScience @epflSV @ChariteBerlin @questbih
1
4
1
19
3,030
Load more