Twitter | Search | |
distillpub
Supporting Clarity in Machine Learning.
78
Tweets
68
Following
11,398
Followers
Tweets
distillpub retweeted
Jeff Dean 2h
This article on Feature Visualization by Chris Olah (), Alexander Mordvintsev (), and Ludwig Schubert () is excellent for understanding what's going inside computer vision machine learning models.
Reply Retweet Like
distillpub Dec 5
Replying to @hmpim @michael_nielsen
We're pretty delighted to have publish an article with us. :)
Reply Retweet Like
distillpub retweeted
Jennifer 💩🌪️ Dec 5
This is the best paper I've read about tech, art, design, ML, and creativity all year, maybe ever. Very excited to just begin and try to internalize this manifesto of sorts. ✨
Reply Retweet Like
distillpub Dec 5
Using Artificial Intelligence to Augment Human Intelligence -- A new Distill commentary article by & .
Reply Retweet Like
distillpub retweeted
michael_nielsen Dec 4
New essay, with , in : "Using Artificial Intelligence to Augment Human Intelligence"
Reply Retweet Like
distillpub retweeted
Károly Zsolnai-Fehér Dec 3
How Do Neural Networks See The World? Pt 2. | Two Minute Papers #211
Reply Retweet Like
distillpub retweeted
Awni Hannun Nov 27
My new article: "Sequence Modeling With CTC" published in !
Reply Retweet Like
distillpub Nov 27
Sequence Modeling With CTC -- A new Distill article by .
Reply Retweet Like
distillpub retweeted
Eric Schmidt Nov 8
Like an MRI for artificial neural nets - this is amazing research on illuminating AI:
Reply Retweet Like
distillpub retweeted
Chris Olah Nov 8
Transformation robustness is a simple way to regularize feature visualization. Try the interactive playground in our article!
Reply Retweet Like
distillpub retweeted
Grant Sanderson Nov 7
New (absolutely beautiful) paper on feature visualization, by , &
Reply Retweet Like
distillpub retweeted
Arfon Smith Nov 7
Surprised & delighted that we're about to hit 250 submissions to JOSS in ~18 months
Reply Retweet Like
distillpub retweeted
Tim Hwang Nov 7
latest piece by on feature visualization in neural networks is AMAZINGGGG
Reply Retweet Like
distillpub retweeted
Chris Olah Nov 7
Replying to @zzznah @ludwigschubert
These "geometry detectors" (in mixed3b & mixed4a) are some of the most interesting channels for me. eg.
Reply Retweet Like
distillpub retweeted
Chris Olah Nov 7
What do neural nets see? You may be surprised. & I explore.
Reply Retweet Like
distillpub retweeted
Jack Clark Nov 7
Profound new ways to visualize what individual neural net neurons (and so much more!) learn, from et al.
Reply Retweet Like
distillpub Nov 7
Feature Visualization - a new Distill article by & .
Reply Retweet Like
distillpub Sep 30
We have a bunch of articles on the way, but getting them perfect takes time. :)
Reply Retweet Like
distillpub Sep 23
Replying to @JohnMannes
We have a bunch of articles 90% done, and a number of other draft articles. Getting them right takes effort and we don't want to rush. :)
Reply Retweet Like
distillpub Aug 25
Mostly . He's *amazing*.
Reply Retweet Like