🥳Alrighty - end-of-year push to get the final version of #CellSeg3D out!
👩💻 pip install napari-cellseg3d==0.2.2
📚 biorxiv.org/content/10.1101/…
We extended benchmarking, new videos, extended text, and a demo on cFOS 👋
Job alert 🚨: I’m looking for a creative, ambitious, and dedicated postdoc to join me on this quest; so many exciting questions about how cortex and sub cortical structures (including spinal cord) drive adaptive motor control.
Large scale 2P (limited labs 🌎 have this tech), plus we have large scale Neuropixels tech (8 probes anyone?)… plus my lab has excellent computational students/postdocs and we work as a team 💪🚀
Please email me (CV & cover letter including why the line of work the paper outlines is a good fit with you profile).
How does sensorimotor (S1/M1) cortex support adaptive motor control?
Come find out in our latest preprint, which spans the development of a full adult forelimb model + physics simulations, neural-modeling for control, complex 🐭behavior 🕹️, large-scale imaging, and of course @DeepLabCut and @CEBRA!
We hypothesized that S1 supports motor learning by computing prediction errors. To tackle this, we needed to understand what is being represented, and no studies have reported what forelimb S1 represents during learning in mice🧠🐭. Moreover, this requires modeling the body🦾: kinematics, torques, force, muscle activations, & proprioception (muscle spindles & GTOs).
After our 7 year journey, we have an answer: S1 & M1 represent muscle-level features. During learning, computational motifs map to functional types (like muscle-encoding), and neural dynamics in S1 change & encode sensorimotor prediction errors!
biorxiv.org/content/10.1101/…
🧵👇
🚀 DLC AI Residents call for 2025! This year, we are doing something a little different to support even more underrepresented individuals 🥰
We are having in-person workshops again 🙌, & we are taking the 2025 AI Residency on the Road! 🛤️
App open now!
deeplabcutairesidency.org/
How does sensorimotor (S1/M1) cortex support adaptive motor control?
Come find out in our latest preprint, which spans the development of a full adult forelimb model + physics simulations, neural-modeling for control, complex 🐭behavior 🕹️, large-scale imaging, and of course @DeepLabCut and @CEBRA!
We hypothesized that S1 supports motor learning by computing prediction errors. To tackle this, we needed to understand what is being represented, and no studies have reported what forelimb S1 represents during learning in mice🧠🐭. Moreover, this requires modeling the body🦾: kinematics, torques, force, muscle activations, & proprioception (muscle spindles & GTOs).
After our 7 year journey, we have an answer: S1 & M1 represent muscle-level features. During learning, computational motifs map to functional types (like muscle-encoding), and neural dynamics in S1 change & encode sensorimotor prediction errors!
biorxiv.org/content/10.1101/…
🧵👇
I'm thrilled to present our paper "Elucidating the Hierarchical Nature of Behavior with Masked Autoencoders" at #ECCV24! 🎉 We focus on self-supervised learning for action segmentation to uncover the hierarchical structure of behavior.
Paper: ecva.net/papers/eccv_2024/pa…
👇🧵
Mackenzie Mathis is the winner of the prestigious Swiss Science Prize #Latsis 2024. It rewards her #research into the neural bases of our learning behaviour. sohub.io/w1mz
📷 Daniel Rihs (images 1 and 4), Mackenzie Mathis Lab (images 2 and 3)
@TrackingActions
We are releasing AmadeusGPT-0.1.3!
Many use cases to demonstrate its capability. We also have invited DLC residents (
@StuckertAnna , @mrc_canela, @dikra_masrour to share their use cases.
Seamless integration with #SuperAnimal and GPT-4o
#FENS2024 is starting tomorrow in Vienna 🇦🇹! Check out where to find us ⬇️
💜As a SuperGroup - @mwmathislab @amathislab - we have 12 posters 🎉 and our joint Kandel Prize Lecture (come cheer us on! 🤩😱)
I am thrilled to share that our paper "SuperAnimal pretrained pose estimation models for behavioral analysis" has just been published at Nature Communications! @mwmathislab nature.com/articles/s41467-0…. More details about our animal pose foundation models:
A new technology developed at EPFL makes it possible for a single deep learning model to detect animal motion across many species and environments. This “foundational model” can be used for animal conservation, biomedicine, and neuroscience research.
actu.epfl.ch/news/unifying-b…
🎉 new preprint posted of potential interest, lead by talented masters student @AChRD4:
🔥fully unsupervised 3D cell segmentation that is as good (or better) than leading supervised methods, with @napari_imaging integration! 👏
biorxiv.org/content/10.1101/…
➕new 3D GT dataset ⬇️🧵