News for hackers. Stuff that matters.
Re:The Limitations of Deep Learning by honestoHeminway on Tuesday July 18, 2017 @04:20AM (#14795055)
Much of the programming with ML has moved towards cleaning, extrapolating and generating the data.

But this type of programing is - miracles- bugfree. We never hear of data-conversion gone wrong, data corrupted or data-mining withou conclusive results here. Obviously such bugs lack the glamour of security bugs.

Re:The Limitations of Deep Learning by skgoa on Tuesday July 18, 2017 @07:14AM (#14795649)
It's also very difficult to catch these errors. Your trained model just doesn't work as well as it could, but how would you be able to tell?