Re:Jeff Dean’s Lecture for YC AI [video]
by iandanforth on Monday August 07, 2017 @05:29PM
(#14951427)
The notion of running one giant model that has many sub-talents is epic. I can imagine that all the disparate models they run today could fuse into a giant network that melds predictions and guides computation as required by the task. That seems like a very Jeff Dean scale endeavor.
[ Parent
| on HN ]
He is referring to this paper https://research.googleblog.com/2017/06/multimodel-multi-tas...
Where they used one model to do image recognition, speech recognition and translation in the same network.
He also mentions sparsely activating only the neurons that matter, which they explore in https://arxiv.org/pdf/1701.06538.pdf
Personally I didn't find it very satisfying, I imagine something more fundamental and self referential.
Re:Jeff Dean’s Lecture for YC AI [video]
by erikpukinskis on Tuesday August 08, 2017 @04:16PM
(#14962068)
It's a great idea, and human beings are proof that conjoined colonies of intelligent agents are going to be smarter than individuals. But it also runs up against tradeoffs, as evidenced by the fact that many humans exist, and we didn't evolve into just one giant ur-human, even after we all got our internet implant. Sometimes a few agents with different strategies working independently is better than a single agent choosing amongst the strategies of several others.
Re:Jeff Dean’s Lecture for YC AI [video]
by soVeryTired on Tuesday August 08, 2017 @12:52PM
(#14959757)
Sounds like a joy to debug