|
Niru Maheswaranathan
@
niru_m
Mountain View, CA
|
|
|
|
|
1.692
Tweetovi
|
783
Pratim
|
1.647
Osobe koje vas prate
|
| Tweetovi |
| Niru Maheswaranathan proslijedio/la je tweet | ||
|
Adam J Calhoun
@neuroecology
|
18. pro |
|
Peering into a deep network trained on retina data:
- Instantaneous RFs are context-dependent and state-based
- Network subspace used by white noise and natural scenes are different
[Nice update from @niru_m @SuryaGanguli]
biorxiv.org/content/10.110… pic.twitter.com/D6vIuvMP5X
|
||
|
|
||
|
Niru Maheswaranathan
@niru_m
|
10. pro |
|
Thank you for the kind words!
|
||
|
|
||
| Niru Maheswaranathan proslijedio/la je tweet | ||
|
Alex Williams🌹
@ItsNeuronal
|
10. pro |
|
Co-presenting this work with @niru_m, @MattGolub_Neuro, @SuryaGanguli, @SussilloDavid now #NeurIPS at poster #156! twitter.com/niru_m/status/…
|
||
|
|
||
|
Niru Maheswaranathan
@niru_m
|
1. pro |
|
Awesome work, congrats @dnag09 ☺️ twitter.com/NEJM/status/11…
|
||
|
|
||
| Niru Maheswaranathan proslijedio/la je tweet | ||
|
Hidenori Tanaka
@Hidenori8Tanaka
|
21. stu |
|
New paper out on #NeurIPS2019: “From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction”
with fantastic collaborators @aran_nayebi, @niru_m, @lmcintosh, Stephen Baccus, @SuryaGanguli.
papers.nips.cc/paper/9060-fro… pic.twitter.com/FvLyTmbZtY
|
||
|
|
||
| Niru Maheswaranathan proslijedio/la je tweet | ||
|
Dr Lila Landowski
@rockatscientist
|
14. stu |
|
Here you can see two neurons sensing one another and connecting in a petri dish.
There are 86 billion neurons in the #brain, and they use these webbed hand like structures (“growth cones”) to search for and connect to other neurons or body parts as we develop
@AcademicChatter pic.twitter.com/TOFLqUThho
|
||
|
|
||
| Niru Maheswaranathan proslijedio/la je tweet | ||
|
David Duvenaud
@DavidDuvenaud
|
11. stu |
|
We approximated the implicit function theorem to tune millions of hyperparameters. Now we can train data augmentation networks from scratch using gradients from the validation loss.
arxiv.org/pdf/1911.02590…
With @JonLorraine and @PaulVicol pic.twitter.com/BUVS4JSWPP
|
||
|
|
||
| Niru Maheswaranathan proslijedio/la je tweet | ||
|
Jessica AF Thompson🧠🤖🤔👩💻✊
@tsonj
|
7. stu |
|
So grateful for @skornblith 's colab on CKA. It seems obvious in retrospect but I hadn't considered the equivalence of calculating similarities based on examples and based on features. My experiments are so much faster now...🚀 twitter.com/skornblith/sta… pic.twitter.com/SJXWjXiLUf
|
||
|
|
||
|
Niru Maheswaranathan
@niru_m
|
7. stu |
|
Loved listening to this interview with Andrew Saxe. Great summaries of a lot of beautiful work! (side note, the previous interviews are just as good--kudos to @pgmid for running a great podcast!) twitter.com/pgmid/status/1…
|
||
|
|
||
| Niru Maheswaranathan proslijedio/la je tweet | ||
|
Shahab Bakhtiari
@ShahabBakht
|
2. stu |
|
No, this isn’t from @tyrell_turing et al recent perspective on @NatureNeuro. This is David Robinson trying to make a similar point in 1992: dna.caltech.edu/courses/cns187… pic.twitter.com/bXJANFMtO9
|
||
|
|
||
|
Niru Maheswaranathan
@niru_m
|
1. stu |
|
#cosyne2020 submission deadline: 31Oct 11:59 **Pacific Time**. #cosyne2020 registration deadline: 31Jan 11:59 **Eastern Time**. (cosyne.org/c/index.php?ti…) pic.twitter.com/taTBBAiY3x
|
||
|
|
||
|
Niru Maheswaranathan
@niru_m
|
1. stu |
|
itermplot (github.com/daleroberts/it…) is a matplotlib backend that displays directly in your terminal (iterm2). Really awesome resource if you (like me) enjoy working directly from the IPython repl! pic.twitter.com/oG0znEelVl
|
||
|
|
||
| Niru Maheswaranathan proslijedio/la je tweet | ||
|
srdjan ostojic
@ostojic_srdjan
|
1. stu |
|
We received ~650 abstracts for #cosyne2020, a number comparable to two years ago in Denver (700), and a big drop wrt Lisbon last year (1000).
|
||
|
|
||
| Niru Maheswaranathan proslijedio/la je tweet | ||
|
Brandon Amos
@brandondamos
|
28. lis |
|
Stoked to share a milestone project for all of us! #NeurIPS2019 paper with @akshaykagrawal, @ShaneBarratt, S. Boyd, S. Diamond, @zicokolter:
Differentiable Convex Optimization Layers
Paper: web.stanford.edu/~boyd/papers/p…
Blog Post: locuslab.github.io/2019-10-28-cvx…
Repo: github.com/cvxgrp/cvxpyla… twitter.com/akshaykagrawal…
|
||
|
|
||
|
Niru Maheswaranathan
@niru_m
|
18. lis |
|
Congrats Arun!
|
||
|
|
||
|
Niru Maheswaranathan
@niru_m
|
6. lis |
|
You’re right, the lab has come a long way since those early days! It’s been a ton of fun watching it grow over the years :)
|
||
|
|
||
|
Niru Maheswaranathan
@niru_m
|
5. lis |
|
Congrats, Surya!!!
|
||
|
|
||
|
Niru Maheswaranathan
@niru_m
|
21. ruj |
|
Interesting! I feel like the use of a diverging colormap is a poor choice—by changing the range used to center the data, you could tell a different story. This article (
blog.datawrapper.de/weekly-chart-g…) by @lisacrost is not about colormaps, but discusses misleading climate visualizations
|
||
|
|
||
|
Niru Maheswaranathan
@niru_m
|
9. ruj |
|
s/algorithms/developments. Matlab is not an algorithm 😅
|
||
|
|
||
|
Niru Maheswaranathan
@niru_m
|
9. ruj |
|
The greatest numerical algorithms of the 20th century, according to Nick Trefethen circa 2005 (people.maths.ox.ac.uk/trefethen/inve…) pic.twitter.com/1okDhTC2Zk
|
||
|
|
||