Twitter | Pretraživanje | |
xaq
Brains, Math, and Art
365
Tweetovi
278
Pratim
585
Osobe koje vas prate
Tweetovi
xaq 3. velj
Odgovor korisniku/ci @data_bayes
Age 6: BASIC Age 12: Pascal Age 15: LISP Age 18: C Age 19: Assembly Age 20: Mathematica Age 23: C++ Age 31: Python
Reply Retweet Označi sa "sviđa mi se"
xaq 2. velj
Odgovor korisniku/ci @KordingLab
How about angles between two random p-dimensional subspaces in n dimensions? min_angle = pi/2 - 2 sqrt(p/n). (Any proofs?) So until p is comparable to n, even subspaces are mostly orthogonal. Yet p/n=1% already shows some alignment, min_angle=79°.
Reply Retweet Označi sa "sviđa mi se"
xaq 2. velj
Odgovor korisniku/ci @RobertRosenba14 @KordingLab
Misleading? The distribution of _distances_ is highly concentrated far from the origin, but the probability density over space is still highest in the middle. There are many ways to be far from the origin but they're each lower probability. Overall, entropy wins.
Reply Retweet Označi sa "sviđa mi se"
xaq 2. velj
Odgovor korisniku/ci @UN_Women @kiara_bellido
Yes. Why? Because what you think, you become.
Reply Retweet Označi sa "sviđa mi se"
xaq 2. velj
Odgovor korisniku/ci @jehosafet
[pronoun] not busy being born is busy dying. -Dylan But there are lots of dimensions to be born and die in.
Reply Retweet Označi sa "sviđa mi se"
xaq 1. velj
Odgovor korisniku/ci @bayesianbrain @KordingLab i 10 ostali
I don't understand the question yet. But one straightforward thought on neural manifold: Bottleneck-then-expansion strongly favors low-D representations in high-D space (though not guaranteed because of possible temporal multiplexing).
Reply Retweet Označi sa "sviđa mi se"
xaq 29. sij
Amazing. Great to see these collected in one place. Such food for thought about thoughts...
Reply Retweet Označi sa "sviđa mi se"
xaq proslijedio/la je tweet
Allen Institute 22. sij
ICYMI: Check out the first analysis of our dataset from our collaboration with & supported by MICrONS 👉
Reply Retweet Označi sa "sviđa mi se"
xaq proslijedio/la je tweet
Yann LeCun 20. sij
I suggest that the name of the American system of measurements (or lack thereof) be changed from "imperial" to "inferial".
Reply Retweet Označi sa "sviđa mi se"
xaq proslijedio/la je tweet
Andreas Tolias Lab 17. sij
Interested in how can help understand and how can advance ? Two weeks left to apply to summer school in beautiful ! Great line of lecturers and hands-on workshop on and data.
Reply Retweet Označi sa "sviđa mi se"
xaq 15. sij
Odgovor korisniku/ci @bayesianbrain @TonyZador i 5 ostali
One example: divisive normalization of 1/x could be done with ReLUs but you need a new neuron for every change in slope. And as x->1 that’s a lot of neurons. Maybe dedicating a special type of neuron is efficient. So sometimes neural details may matter.
Reply Retweet Označi sa "sviđa mi se"
xaq 15. sij
Odgovor korisniku/ci @bayesianbrain @TonyZador i 5 ostali
More fine neural detail may only improve computation by a small factor, as if 3N neurons not N. But combined with biological constraints (esp. learning dynamics) it could be crucial!
Reply Retweet Označi sa "sviđa mi se"
xaq 15. sij
Odgovor korisniku/ci @bayesianbrain @TonyZador i 5 ostali
I agree that neurons are powerful little critters working on many timescales. I tend to think more about networks and wash out most details like an obedient stat physicist.
Reply Retweet Označi sa "sviđa mi se"
xaq proslijedio/la je tweet
Maria Neimark Geffen 14. sij
Come spend three weeks learning about Computational Neuroscience in sunny Lisbon this summer!
Reply Retweet Označi sa "sviđa mi se"
xaq 8. sij
Great fun, great neuroscience! Plus: longer tutorials the day before by the speakers, to help prepare you for their main presentation and learn modern quantitative tools!
Reply Retweet Označi sa "sviđa mi se"
xaq 8. sij
Trajectories in a smooth random gaussian field.
Reply Retweet Označi sa "sviđa mi se"
xaq proslijedio/la je tweet
David Schneider 6. sij
Just over 1 week left to apply for a faculty position at NYU's Center for Neural Science (due by January 15th)!
Reply Retweet Označi sa "sviđa mi se"
xaq proslijedio/la je tweet
Blake Richards 6. sij
*REMINDER + PLS RT* Our workshop, From Neuroscience to Artificially Intelligent Systems (NAISys), has an abstract deadline of January 10. This Friday!!! But, it's only 1-page, so easy-peasy: Please send in ideas for how neuroscience can inform AI!
Reply Retweet Označi sa "sviđa mi se"
xaq proslijedio/la je tweet
Franco Ronconi 4. sij
Reply Retweet Označi sa "sviđa mi se"
xaq proslijedio/la je tweet
Emily Roberts, PhD 4. sij
OK this may seem weird but it’s actually really important. -specific tax info coming your way! 1/15
Reply Retweet Označi sa "sviđa mi se"