Re:Nvidia Pascal GPU Architecture to Provide 10X Speedup fo...
by soup10 on Monday May 18, 2015 @07:09AM
(#9563731)
I think it depends on the algorithm. Something like siri trains on a larger data set with better hardware and uses a reduced version on the phone hardware. I think most neural networks can be reduced and compressed into a 'read only' format with limited or no new training, but it's a secondary problem.
[ Parent
| on HN ]
There are no comments on this comment yet.