@fchollet doesn't that include DQN/A3C? 
... seems like super-human performance may be a thing of the past.https://twitter.com/fchollet/status/1023722208508530688 …
-
In one case you have natural program synthesis -- you look at something and immediately, unconsciously come up with an abstract model of it and rules for solving it, and in the other case you have a deliberately engineered program synthesis algorithm.
This is like comparing biological vision with deep learning. Just because humans have created deep learning systems to recognize objects doesn't mean that these systems are in the same category as the natural object recognition capabilities of humans.
-
-
Of course you understand these things perfectly well.
-
I think it's an interesting question... Seems like there are at least three reasonable benchmarks for "human performance": 1 - Human playing the game (current score) 2 - Human playing without reaction time problems 3 - Human-crafted strategy "simple" program <- your suggestion?
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.