Beautiful day in Cambridge, catching up on reading! Recommend articles on Google's "deep dream"? (Finally read more about it; fascinating).
-
-
Replying to @zeynep
Just realized that the Google cat recognition paper is... merely five years old. A doctoral student who started before may not even be done.
2 replies 2 retweets 15 likes -
Replying to @zeynep
A lot of people refer to deep learning papers from 2014 as "classic"
2 replies 3 retweets 31 likes -
Replying to @goodfellow_ian
Yeah. The speed makes it hard for people to distinguish what's going on now from hype. But amazing to just think through last few years.
1 reply 0 retweets 2 likes -
Replying to @zeynep
Yes, it's also amazing to see how well some work from the 1950s and 1980s has held up
1 reply 0 retweets 1 like -
Replying to @goodfellow_ian
Perceptron ftw. :-) But who had "dot product" on the bingo card as an operation in the thick of societal transformations & ethical dilemmas?
1 reply 0 retweets 3 likes
Fascinatingly different than the way physics in first half of the 20th century changed so much. Very hard problems, but different class.
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.