Sign in

Janne Lappalainen

@lappalainenjk.bsky.social
168 followers 225 following 10 posts

machine learning, connectomics, comp neuro

PostsRepliesMedia
Reposted by Janne Lappalainen
Stephan Saalfeld @herrsaalfeld.bsky.social · 12/03/2026
Friday, 13:15 (Poster 2-048) at @cosynemeeting.bsky.social #cosyne2026: @allierced.bsky.social and @lappalainenjk.bsky.social present how they made GNNs learn interpretable circuit models from neural activity. Code: saalfeldlab.github.io/flyvis-gnn/
saalfeldlab.github.io
Graph Neural Networks Recover Interpretable Circuit Models from Neural Activity – FlyVis-GNN
0105
Janne Lappalainen @lappalainenjk.bsky.social · 09/03/2026
My dissertation is just out today: hdl.handle.net/10900/176447 Timely for the current discussion. It covers predicting neural function underlying behavior with connectomes & ML, why single models aren't enough, and remaining challenges for whole-brain simulation (e.g. Chapter 4.1.1).
4160
Reposted by Janne Lappalainen
Machine Learning in Science @mackelab.bsky.social · 13/11/2025
Our work on training biophysical models with Jaxley is now out in @natmethods.nature.com. Led by @deismic.bsky.social, with @philipp.hertie.ai, @ppjgoncalves.bsky.social & @jakhmack.bsky.social et al. Paper: www.nature.com/articles/s41...
nature.com
Jaxley: differentiable simulation enables large-scale training of detailed biophysical models of neural dynamics - Nature Methods
Jaxley is a versatile platform for biophysical modeling in neuroscience. It allows efficiently simulating large-scale biophysical models on CPUs, GPUs and TPUs. Model parameters can be optimized with ...
14825
Reposted by Janne Lappalainen
Janelia Research Campus @hhmijanelia.bsky.social · 23/07/2025
🪰 A new ‘Eyemap’ developed by a team led by Arthur Zhao & @michaelreiser.bsky.social reveals how visual information detected by the fly’s eye shows up in neurons deep in the brain. Remarkably, the eye’s shape determines how flies see motion.👁️ 🔗 hhmi.news/4kSZjou
410022
Reposted by Janne Lappalainen
The Transmitter @thetransmitter.bsky.social · 23/07/2025
Computational sciences can offer a unique opportunity for democratized access and participation, but we are currently falling far short of that goal, writes @neuromatch.bsky.social's @meganakpeters.bsky.social and Bradley Roberts‬‬‬‬. #neuroskyence www.thetransmitter.org/education/ho...
thetransmitter.org
How to build a truly global computational neuroscience community
Computational sciences offer an opportunity to increase global access to, and participation in, neuroscience. Neuromatch’s inclusive, scalable model for community building shows how to realize this…
02010
Reposted by Janne Lappalainen
T. Anderson Keller @andykeller.bsky.social · 10/03/2025
In the physical world, almost all information is transmitted through traveling waves -- why should it be any different in your neural network? Super excited to share recent work with the brilliant @mozesjacobs.bsky.social: "Traveling Waves Integrate Spatial Information Through Time" 1/14
314943
Reposted by Janne Lappalainen
CAJAL Training @cajal-training.bsky.social · 03/02/2025
🚀 Applications are OPEN for the CAJAL NeuroAI course! Learn how AI & deep learning help us model brain activity & behavior. Work with experts, get hands-on training & join a global network! 📅 Apply by March 7 🔗 loom.ly/xg_uRKE #NeuroAI #DeepLearning #Neuroscience
22411
Reposted by Janne Lappalainen
Jan Funke @janfunkey.bsky.social · 15/01/2025
How can we use machine learning to find subtle patterns in our data and have them visualized? Read the thread below to find out how! Or head to @adjavon.bsky.social's blog post and let Simon the duck walk you through it (like a duck of course): tinyurl.com/yy7csdcd www.biorxiv.org/content/10.1...
biorxiv.org
Quantitative Attributions with Counterfactuals
We address the problem of explaining the decision process of deep neural network classifiers on images, which is of particular importance in biomedical datasets where class-relevant differences are no...
0175
Janne Lappalainen @lappalainenjk.bsky.social · 30/12/2024
Ever wanted to do deep learning with a neural net that is one-to-one mapped to 65.05% of the fruit fly brain? 😄 Before this year ends, I will quickly advertise our code release of `flyvis.` Docs: t.ly/YqWzR Repo: t.ly/pMWpp Work with @jakhmack.bsky.social, @srinituraga.bsky.social and colleagues
Screenshot of the docs at turagalab.github.io/flyvis
14817
Reposted by Janne Lappalainen
Grace Lindsay @neurograce.bsky.social · 26/12/2024
Thinking about this a lot as a (pre-tenure) PI. There just isn't enough time to go deeply into an idea, which is obviously bad for (my) science.
210311
Janne Lappalainen @lappalainenjk.bsky.social · 21/12/2024
Why study the fruit fly brain? Tech giants spend billions on gigantic neural networks, but there’s a fruit fly with only 130_000 neurons that can do so much more and runs on less power than a quartz watch.
3204