Re:Machine learning saves us $1.7M a year on document previews
by lspears on Wednesday January 27, 2021 @07:53PM
(#25936617)
The more interesting problem is learning doc -> image directly. With Dropbox's scale of data, seems feasible for some data types.
[ Parent
| on HN ]
Re:Machine learning saves us $1.7M a year on document previews
by caturopath on Wednesday January 27, 2021 @08:00PM
(#25936679)
I'm sure that couldn't leak anything important.