For most problems where deep learning has enabled transformationally better solutions (vision, speech), we've entered diminishing returns territory in 2016-2017
-
-
We should def be assessing it by log accuracy: there is a great report about the development of AI here: http://aiindex.org/2017-report.pdf
-
And the improvements in imagenet in the few years: https://qz.com/1034972/the-data-that-changed-the-direction-of-ai-research-and-possibly-the-world/ …
End of conversation
New conversation -
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.