NIPS 1990 had papers about "hybrid symbolic-connectionist" models. This is now as far in the past as 2050 is in the future.pic.twitter.com/4PkkuHBSrA
You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
Assuming linear progression and not geometric. 
If you look at NIPS 1993, you really see how everything old is new again: https://papers.nips.cc/book/advances-in-neural-information-processing-systems-6-1993 …
And yet if you look at NIPS 2009, you will see almost nothing recognizable in there.
It’d be good to track what become spread knowledge to the point the community might not acknowledge it's intrinsic importance. I'd guess graphical models
How about "SEXNET: A Neural Network Identifies Sex From Human Faces" http://papers.nips.cc/paper/405-sexnet-a-neural-network-identifies-sex-from-human-faces … Feels like such things wouldn't be acceptable today?pic.twitter.com/PCXt4KZ8Ze
The Age of Intelligent Machines is from 1990 too https://en.wikipedia.org/wiki/The_Age_of_Intelligent_Machines … It is as valid now as it was in 1990 and it will be in 2050, a classic The singularity will always be near in our hearts
Coincidence is everything but the year 1990 was also "Annus Mirabilis" of deep learning according to Schmidhuber
http://people.idsia.ch/~juergen/deep-learning-miraculous-year-1990-1991.html …
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.