Re:Why Are Eight Bits Enough for Deep Neural Networks?
by Animats on Saturday September 19, 2015 @03:43PM
(#10245326)
That's fascinating, especially since very slow training, where the weights don't change much per cycle, is in fashion. One would think that would result in changes rounding down to zero and nothing happening, but apparently it doesn't.
[ Parent
| on HN ]
There are no comments on this comment yet.