News for hackers. Stuff that matters.

A comment on How a Toronto professor’s research revolutionized artificial intelligence. Parent comment

Re:How a Toronto professor’s research revolutionized artific... by murbard2 on Friday April 17, 2015 @04:56PM (#9397161)
Not so much the computing power as a few tricks:

- proper initialization of weights (should have been obvious, but no one really saw it)

- rectified linear units and dropout

[ Parent | on HN ]
Re:How a Toronto professor’s research revolutionized artific... by UmDieWelt on Friday April 17, 2015 @05:27PM (#9397285)
Also, a lot more data to train on.
[ Parent | on HN ]