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
"Ever bigger steam engines burning ever more coal is the superior approach to build faster trains", they said. More data + scaling up simple algos will get you better models, obviously. But there are diminishing returns -- meanwhile, new approaches can be transformational
I guarantee you that the dominant AI algorithm of the 2050s will not be a stack of differentiable layers trained with SGD.
At this point we are pretty close to training our language models on the entirety of text corpora that humanity has produced so far. Their language understanding capabilities are still close to zero.
Lets hear some speculation! could it still be powered by keras?
On the other hand, it's 2019 and I'm still on a Unix-like operating system written in C.
All hail genetic algorithms and reinforced learning!
these approaches are even less data efficient than sgd,
Cannot agree more. Mad rush toward more and more data and customized hardware based on 20-25 year old methods with obvious potentially fatal flaws...
We could be stuck in this local minima for a long time.
You are right
Sounds like yet one more revolution in ML. But what alternative for SGD and stacks may be in 2050s? Sorry, if it silly question.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
