Marius Pachitariu
Lab head @HHMIJanelia
neuroscience, deep learning, large-scale recordings
#Kilosort, #Suite2p, #Cellpose, #Rastermap, #Facemap
- Reposted by Marius PachitariuExcited to share “Orofacial behaviors, not eye movements, govern neural activity in mouse visual cortex” www.biorxiv.org/content/10.6... Summary below...
- Reposted by Marius PachitariuA System for Live Sorting of Neuronal Spiking Activity from Large-scale Recordings biorxiv.org/content/10.64898/20…
- Reposted by Marius Pachitariu[Not loaded yet]
- Reposted by Marius PachitariuI have so many issues with this podcast with @earlkmiller.bsky.social . I think that this podcast nicely shows why I have trouble with such approaches. Lets go through some of the claims.
- Reposted by Marius PachitariuStill beta-testing the app that helps people plan science, make it super clear, design their todos, and write a first version of the paper. Feeling overwhelmed by the countless aspects of doing science? Try this (for free): planyourscience.com
- Reposted by Marius PachitariuEven colleagues who should know better are claiming that we are halting animal research. No, we're not. Now this NYT opinion piece appears (gift link) www.nytimes.com/2025/10/08/o... You can't just move everything to cell culture, organoids, and computers. Even this NYT piece admits that. 1/3
- Reposted by Marius PachitariuIs visual cortex more like chatGPT or a masked autoencoder? Come to my BCCN seminar tomorrow at 10am ET on zoom (or read the paper) to find out! #neuroscience Zoom: urldefense.com/v3/__https:/... Paper: www.biorxiv.org/content/10.1...
- Does predictive coding work in SPACE or in TIME? Most neuroscientists assume TIME, i.e. neurons predict their future sensory inputs. We show that in visual cortex predictive coding actually works across SPACE, just like the original Rao+Ballard theory #neuroscience www.biorxiv.org/cgi/content/...
- New work from the lab, mismatch responses consistent with spatial but not temporal predictive coding theory.
- Does predictive coding work in SPACE or in TIME? Most neuroscientists assume TIME, i.e. neurons predict their future sensory inputs. We show that in visual cortex predictive coding actually works across SPACE, just like the original Rao+Ballard theory #neuroscience www.biorxiv.org/cgi/content/...
- Reposted by Marius PachitariuDoes predictive coding work in SPACE or in TIME? Most neuroscientists assume TIME, i.e. neurons predict their future sensory inputs. We show that in visual cortex predictive coding actually works across SPACE, just like the original Rao+Ballard theory #neuroscience www.biorxiv.org/cgi/content/...
- Reposted by Marius Pachitariu💻A new class of simplified ‘minimodels’ developed by Fengtong Du, Miguel Angel Núñez-Ochoa, @marius10p.bsky.social & @computingnature.bsky.social can predict the visual responses of individual neurons in the primary visual cortex, helping shed light on how we see.👀 ➡️ www.janelia.org/news/new-com...
- Reposted by Marius PachitariuDoing this might make you smarter ... (www.vice.com/en/article/d...) News coverage of our study on unsupervised learning in mice by @zhong-lin.bsky.social + @marius10p.bsky.social #neuroscience #AI www.nature.com/articles/s41...
- Reposted by Marius Pachitariu🧠Zoning out could be beneficial—and may actually help us learn faster. 🥼New research led by @zhong-lin.bsky.social @marius10p.bsky.social @computingnature.bsky.social 🔗 www.janelia.org/news/zoning-...
- Your brain learns for you even when you're not actively learning. Maybe. (in mice).
- 🚶Aimlessly wandering around a city or exploring the new mall may seem unproductive, but new research led by @zh0ng0.bsky.social @marius10p.bsky.social @computingnature.bsky.social suggests it could play an important role in how our brains learn. 🧠 🔗 www.janelia.org/news/zoning-...
- Reposted by Marius PachitariuOur paper on NHP neuropixels is finally out in Nat Neuro! These probes have already been transformative and will usher in a new era of primate neuroscience. I am extremely proud to have played a very small role in this project. I can't wait to see what our community discovers. tinyurl.com/54u3hrj8
- Reposted by Marius Pachitariu[Not loaded yet]
- Reposted by Marius Pachitariu🚶Aimlessly wandering around a city or exploring the new mall may seem unproductive, but new research led by @zh0ng0.bsky.social @marius10p.bsky.social @computingnature.bsky.social suggests it could play an important role in how our brains learn. 🧠 🔗 www.janelia.org/news/zoning-...
- Reposted by Marius PachitariuEveryone in the lab is raving about Cellpose-SAM. Segmenting the previously unsegmentable across a range of different cell types and markers.
- 🚀🔬🦠 Releasing 🤖Cellpose-SAM🤖, a cellular segmentation algorithm with superhuman generalization 🦸♀️. Try it now on 🤗 huggingface.co/spaces/mouse... paper: www.biorxiv.org/content/10.1... w/ @computingnature.bsky.social 1/n
- Reposted by Marius PachitariuWouldn't it be great if we could not only image large connectomic volumes but also completely reconstruct them? And if a whole mouse brain project didn't cost billions? With the PATHFINDER preprint (www.biorxiv.org/content/10.1...), we preview a future where it doesn't have to.
- Reposted by Marius Pachitariu[Not loaded yet]
- Reposted by Marius PachitariuIf you're planning a course with mathematical methods content, or use such methods in your own work, please take a look at "Mathematics in Biology", by Meister, Lee, and Portugues, published at MIT Press. 1/2 @portugueslab.bsky.social mitpress.mit.edu/978026204940...
- Reposted by Marius Pachitariuwe're crowd-sourcing a searchable repository of tangible benefits stemming from federally-funded research. Come enjoy the great stories; or send in an idea; or volunteer to join the team. publicusaresearchbenefits.com please share and re-share so we get more great stories in there!
- 🚀🔬🦠 Releasing 🤖Cellpose-SAM🤖, a cellular segmentation algorithm with superhuman generalization 🦸♀️. Try it now on 🤗 huggingface.co/spaces/mouse... paper: www.biorxiv.org/content/10.1... w/ @computingnature.bsky.social 1/n
- We combined: 1) SAM, a pretrained foundation model with good generalization properties. 2) Cellpose, a good cellular segmentation framework.
- Cellpose-SAM outperforms human-to-human agreement and approaches an estimated absolute bound on performance.
-
View full threadIf you want to learn more, watch the talk or read the paper! talk: www.youtube.com/watch?v=KIdY... paper: www.biorxiv.org/content/10.1... website: huggingface.co/spaces/mouse... github: github.com/MouseLand/ce...
- Reposted by Marius Pachitariu[Not loaded yet]
- Reposted by Marius Pachitariu🚨 Neuromatch Academy Course Applications are OPEN for 2025!! 🚨 Get your application in early to be a student or teaching assistant for this year’s courses! Applications are due Sunday, March 23. Apply & learn more: neuromatch.io/courses/ #mlsky #compneurosky #ai #climatesolutions #ScienceEdu 🧪
- Reposted by Marius PachitariuBring your samples into focus! A new version of the #Cellpose cell boundary mapping tool, developed at @hhmijanelia.bsky.social by @computingnature.bsky.social and @marius10p.bsky.social, now works on less-than-perfect microscopy images that are noisy, blurry, or undersampled.
- Reposted by Marius Pachitariu[Not loaded yet]
- Reposted by Marius Pachitariu#Cellpose 3 paper now out. Not all images are perfect. Restore your images with Cellpose3 to get better segmentations, w/ @marius10p.bsky.social www.nature.com/articles/s41...
- Reposted by Marius Pachitariu[Not loaded yet]
- The trilogy is complete.
- #Cellpose 3 paper now out. Not all images are perfect. Restore your images with Cellpose3 to get better segmentations, w/ @marius10p.bsky.social www.nature.com/articles/s41...
- Reposted by Marius PachitariuTutorial talk here: youtu.be/TZZZlGk6AKo?... ; Code is here: github.com/MouseLand/ce...
- Reposted by Marius PachitariuInterested in understanding how things work? In particular the tools you use to study the brain? Join us at TENSS 2025 where we brainstorm ideas, build and debug microscopes, electrophysiology and behavior rigs amidst the picturesque Transylvanian hills! tenss.ro Apply by: February 16th!
- Reposted by Marius PachitariuWhat if… spontaneous neural activity 🧠 reflects the baseline rumblings of a brainwide dynamical system initialized for learning? We find that the rumblings have macroscopic properties like those emerging from linear symmetric, critical systems 🧵 #neuroscience #neuroAI www.biorxiv.org/content/10.1...