Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @scott_linderman
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @scott_linderman
-
Scott Linderman proslijedio/la je Tweet
I'm pleasantly surprised by the interest in my recent preprint here on Twitter. Feedback or questions are appreciated! https://twitter.com/search?q=arxiv.org%2Fabs%2F2001.09122&f=live …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Congrats Greg — well done!https://twitter.com/guitchounts/status/1218546747548585989 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
New work from a really fun collaboration with
@DavidZoltowski and@jpillowtime! We recast many decision making models as instances of recurrent switching linear dynamical systems. Then we can fit these models to neural data more easily and generalize them in cool new ways!https://twitter.com/DavidZoltowski/status/1217925709340872704 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Scott Linderman proslijedio/la je Tweet
Optimal Transport is a super cool and underutilized tool in neural data analysis. This blog post does a great job introducing it in the case of fMRI data
https://twitter.com/LYTarhan/status/1217196598138036224 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Scott Linderman proslijedio/la je Tweet
The outcome of the
#cosyne2020 review process will be announced soon. To adjust expectations, here is some data and information. 1/nPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Scott Linderman proslijedio/la je Tweet
[urban meyer shown] [ohio state immediately loses]
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
My only complaint: isn't "emergent property" just a fancy name for a statistic?
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
This work is super similar to the likelihood free inference methods from
@jakhmack's group. (See their STG analysis for comparison. Really, everyone's favorite!) https://twitter.com/jakhmack/status/1194316946931621889 … and https://www.biorxiv.org/content/10.1101/838383v1 …Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
They apply the method to a bunch of neat examples: the somatogastric ganglion (everyone's favorite), a four-population model of V1, a task switching model of SC, and abstract RNNs trained to perform posterior inference.pic.twitter.com/kH9pufAd9y
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Enjoyed this new work from Sean Bittner et al. They use normalizing flows to approximate a max-ent distribution over parameters of a black box model, subject to the constraint that the model produce a specified "emergent property" of interest. https://twitter.com/cu_neurotheory/status/1205251287685701632 …pic.twitter.com/SGN0dC0G76
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Scott Linderman proslijedio/la je Tweet
Wired on
@blaiseaguera and Yoshua Bengio's NeurIPS talks and the potential for deeper biological inspiration in AI.https://www.wired.com/story/sobering-message-future-ai-party/ …Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Scott Linderman proslijedio/la je Tweet
Excited to announce voltage imaging in awake mice with ASAP3, out today in Cell. ASAP3 works in 1p or 2p, with random-access 2p producing >5-min recordings in vivo, a collaborative effort with the Dieudonné lab. Plasmids at addgene. https://authors.elsevier.com/a/1aDRcL7PXYX1-#.XfKMDzjd7Po.twitter … https://addgene.org/search/catalog/plasmids/?q=ASAP3 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Here's the paper: https://papers.nips.cc/paper/9206-scalable-bayesian-inference-of-dendritic-voltage-via-spatiotemporal-recurrent-state-space-models … Check out Ruoxi's talk tomorrow and poster on Wednesday morning (#147) to learn more!
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
If you've heard me talk about research over the past few years, you know I can't get enough of switching linear models like these! We've been working on a variety of methods for approximate Bayesian inference, and they work here too.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The key idea is that only the within-compartment dynamics are nonlinear; the coupling between compartments is all linear. By approximating within-compartment dynamics with a recurrent SLDS, the whole cell's voltage follows conditionally linear dynamics.pic.twitter.com/iNT3Cp4CTr
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Finally, Ruoxi Sun is giving an oral presentation (!!!) on our recurrent state space models for spatiotemporal voltage imaging data tomorrow at 4:10pm, W Ballroom C. We use coupled rSLDS to approximate biophysical models of voltage propagation, like this Hodgkin-Huxley model.pic.twitter.com/maHoqoLBx0
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
This tutorial was fantastic. Highly recommend you check out the slides.https://twitter.com/ArthurGretton/status/1204280590901493760 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I'm chairing tomorrow afternoon's session on deep generative models (Track 1 Session 2 @ 4:10pm in Hall C+B3). We have a great line-up of talks! If you have questions for either of the oral presentations, feel free to ask them https://openreview.net/forum?id=B1lcYrBgLH … orhttps://openreview.net/forum?id=S1gqv4rlUB …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Also, I just noticed that we'll be right next door to
@rtqichen and@DavidDuvenaud! Looking forward to catching up and hearing about your latest work!Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Come by
@ifaposto's poster tomorrow (#55, 10:45am) to learn about "Mutually Regressive Point Processes" — nonlinear Hawkes processes with additive excitation and mult. inhibition. If you're into augmentation schemes, you'll def. like our Gibbs sampler! https://neurips.cc/Conferences/2019/Schedule?showEvent=13654 …pic.twitter.com/3FW3k6KNkl
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.