Could you elaborate? After running for days / weeks/ months the output is a net that can do inference in seconds, or with some now-common techniques milliseconds with only small reductions in accuracy. These nets can then be deployed to phones to solve a rapidly increasing number of identification tasks, everything from plants to cancer.
The time from theoretical paper to widely deployed app is smaller in DL than in any other field I have experience with.
The time from theoretical paper to widely deployed app is smaller in DL than in any other field I have experience with.