Piotr Sokol
@MannyDePresso
Followers
458
Following
17K
Media
44
Statuses
2K
Do you work in AI? Do you find things uniquely stressful right now, like never before? Haver you ever suffered from a mental illness? Read my personal experience of those challenges here: https://t.co/OFZmSizl6f
docs.google.com
200Bn Weights of Responsibility The Stress of Working in Modern AI Felix Hill, Oct 2024 The field of AI has changed irrevocably in the last 2 years. ChatGPT is approaching 200m monthly users. Gemini...
37
107
706
Kernel Operator-Theoretic Bayesian Filter for Nonlinear Dynamical Systems
0
1
37
How can we train biophysical neuron models on data or tasks? We built Jaxley, a differentiable, GPU-based biophysics simulator, which makes this possible even when models have thousands of parameters! Led by @deismic_, collab with @CellTypist @ppjgoncalves
biorxiv.org
Biophysiscal neuron models provide insights into cellular mechanisms underlying neural computations. However, a central challenge has been the question of how to identify the parameters of detailed...
2
42
143
How much info in population activity on latents? I'm presenting at @eusipco2024 Jeon, H., & Park, I. M. Quantifying Signal-to-Noise Ratio in Neural Latent Trajectories via Fisher Information. European Signal Processing Conference https://t.co/gvaFJt5z2g
#compneuro #tweeprint
2
11
43
Textbook: "31 Lectures on Geometric Mechanics" (by Darryl D. Holm):
arxiv.org
These lecture notes in geometric mechanics are meant to convey insight through clear definitions and workable examples. The lecture format adopted here is intended to convey the immediacy of the...
2
36
149
A new edition of Zotero, Zotero 7, has been released. It is the biggest update in Zotero’s 18-year history, and the company describes it as a major leap forward in design, performance, and functionality. https://t.co/AnuHwRBtHS
3
57
226
🚨 New paper alert! Have you ever suspected that spikes, Dale's law, and E/I balance might be more than just biological constraints, but rather fundamental to how brains compute? Check out my latest work with Christian Machens @Neuro_CF: https://t.co/5lZ8TlDmIE 🧵 (1/5)
4
31
94
Training dynamical VAEs for neural data to infer the latent dynamics can be costly. Moreover, you can't reuse the components of the trained VAE easily for another dataset. It'd be nice to use it across sessions & animals. Can we simply re-align the VAE? #ICLR2024 @AyeshaVermani
2
18
71
What’s a perfect album that came out when you were 16?
0
0
2
I will be hiring through #ELLIS this year: 3 fully-funded PhD positions for troublemakers in #ML #AI who want to design the next gen of #probabilistic #models and #programs that are provably #reliable and #efficient Join https://t.co/0zZpeXUgZ4
@InfAtEd Email me! Please share!
The portal is open: Our #ELLISPhD Program is now accepting applications! Apply by November 15 to work with leading #AI labs across Europe and choose your advisors among 200 top #machinelearning researchers! #JoinELLISforEurope #PhD #PhDProgram #ML
3
30
95
Tangentially, is the tacit assumption in the community that Riemannian geometry is the correct language to discuss neural manifolds?
@DrYohanJohn Hm. Not so much about RG in general, moreso that the geometry of neural manifolds/trajectories was used as explanations in a number of talks/posters. Very much the Hopfieldian view per @DLBarack and @blamlab
0
1
3
Theory of the donut, or how I stopped worrying and loved geometric quantization
As Euclid famously quipped, there's no royal road to geometry. Especially for undergraduates it's not easy to find suitable resources to learn modern geometry. This undergraduate text, which is just about to be published, provides an introduction to algebraic curves and... (1/3)
0
0
3
I’m a UBC doctoral candidate seeking study participants for my dissertation research on human-feline relationships in the home. If you are interested in participating or learning more about the study, please visit https://t.co/BtUi2MykAf. 🐱Please share widely!🐱
400
3K
6K