Twitter | Pretraživanje | |
David Sussillo ☝️🤓
Computational neuroscience / deep learning. Scientist at Google Brain, adjunct prof at Stanford. All my tweet are belong to me. 😋🍑🍃
1.256
Tweetovi
426
Pratim
7.830
Osobe koje vas prate
Tweetovi
David Sussillo ☝️🤓 proslijedio/la je tweet
Timothy Verstynen 27. sij
I think the real lesson of places like DeepMind, Janelia, and Allen Brain Inst. is the amazing things scientists can do when you actually give them the resources they need to do their work properly, instead of spending so much energy hustling for cash/resources.
Reply Retweet Označi sa "sviđa mi se"
David Sussillo ☝️🤓 proslijedio/la je tweet
Janelle Shane 26. sij
I am making these neural net horseradish brownies and I regret everything
Reply Retweet Označi sa "sviđa mi se"
David Sussillo ☝️🤓 24. sij
Odgovor korisniku/ci @DavidSabatini2 @andpru i 3 ostali
More broadly, I suspect that policing bad science on Twitter isn’t going to stop bad science. For egregious cases I follow and also get a kick out of but these accounts serve very different purposes than what was implied by Andrew’s original poll.
Reply Retweet Označi sa "sviđa mi se"
David Sussillo ☝️🤓 24. sij
Odgovor korisniku/ci @DavidSabatini2 @andpru @wusmsl
Criticism of preprints on Twitter seems particularly pernicious because the work isn’t finished yet and comments that are ever-lasting & widely distributed could have disproportionately negative effects on publication.
Reply Retweet Označi sa "sviđa mi se"
David Sussillo ☝️🤓 24. sij
Odgovor korisniku/ci @andpru @wusmsl
‘Criticize privately, praise publicly’ is my motto.
Reply Retweet Označi sa "sviđa mi se"
David Sussillo ☝️🤓 24. sij
Odgovor korisniku/ci @andpru @wusmsl
Sure! If you know the authors well enough.
Reply Retweet Označi sa "sviđa mi se"
David Sussillo ☝️🤓 24. sij
Odgovor korisniku/ci @andpru @wusmsl
Emphatically NOT twitter.
Reply Retweet Označi sa "sviđa mi se"
David Sussillo ☝️🤓 23. sij
Odgovor korisniku/ci @ang3loliveira
Yes! We used a well known bag-of-words baseline that is interpretable.
Reply Retweet Označi sa "sviđa mi se"
David Sussillo ☝️🤓 23. sij
Odgovor korisniku/ci @SuryaGanguli
A+ tweet
Reply Retweet Označi sa "sviđa mi se"
David Sussillo ☝️🤓 22. sij
Odgovor korisniku/ci @SaberaTalukder
Like linear regression but squishier.
Reply Retweet Označi sa "sviđa mi se"
David Sussillo ☝️🤓 22. sij
Today is the first day I have ever used logistic regression. 😱
Reply Retweet Označi sa "sviđa mi se"
David Sussillo ☝️🤓 proslijedio/la je tweet
eLife - the journal 10. sij
The unexpected discovery that the brain area responsible for hand and arm movements is also active during speech suggests a new way to help restore lost speech
Reply Retweet Označi sa "sviđa mi se"
David Sussillo ☝️🤓 30. pro
Odgovor korisniku/ci @neurograce
Fair. But it depends on what the deep net is doing. 10 years ago we didn’t even understand RNNs that did very simple things and we barely knew how to build them.
Reply Retweet Označi sa "sviđa mi se"
David Sussillo ☝️🤓 30. pro
Odgovor korisniku/ci @neurograce
I wonder if Larry wouldn’t significantly revise some of this, given the progress in model building over the past decade.
Reply Retweet Označi sa "sviđa mi se"
David Sussillo ☝️🤓 28. pro
Odgovor korisniku/ci @latimerkw @KordingLab @jmourabarbosa
I completely agree that dimensionality is the the current problem. We are beginning to contend with it though.
Reply Retweet Označi sa "sviđa mi se"
David Sussillo ☝️🤓 27. pro
Odgovor korisniku/ci @KordingLab @jmourabarbosa
As if I have a definition of understanding. People design linear systems. There’s a whole subfield of engineering dedicated to filters, which iir jargon fir linear system design. If building something isn’t understanding, nothing is.
Reply Retweet Označi sa "sviđa mi se"
David Sussillo ☝️🤓 27. pro
Odgovor korisniku/ci @KordingLab @jmourabarbosa
Wrong. While it is true that one can always linearize locally, it remains a surprising empirical fact for RNNs that the volume where the linearization is valid often sheds meaningful light on the nonlinear computation. That was not necessarily going to be true a priori.
Reply Retweet Označi sa "sviđa mi se"
David Sussillo ☝️🤓 27. pro
Odgovor korisniku/ci @markdhumphries
I don’t regret “prerequisite” insofar as it forced the issue but I agree the word is too strong.
Reply Retweet Označi sa "sviđa mi se"
David Sussillo ☝️🤓 27. pro
Odgovor korisniku/ci @dileeplearning
Me thinking about brains and artificial neural networks.
Reply Retweet Označi sa "sviđa mi se"
David Sussillo ☝️🤓 27. pro
The Falses have it by a 3:1 margin. For my part I would have voted True. That is, we’ll have chewed through what DL has to offer conceptually long before understanding biological neural computation and the exercise will have been invaluable.
Reply Retweet Označi sa "sviđa mi se"