News for hackers. Stuff that matters.
Re:Accelerating Deep Neuroevolution: Train Atari in Hours on... by singhrac on Monday April 23, 2018 @02:10PM (#16905895)
I think the intended implication is that it's accessible to individual researchers that don't work at Facebook/Brain/DeepMind with gigantic clusters (and the engineers able to maintain those clusters). Unfortunately deep learning is still expensive, but many areas of science are (most biology research, high energy physics, etc.). That's why we have grants.

There are no comments on this comment yet.