I second this question. Just as I don't think we can rule out deep learning as a path to AGI, I don't think we can argue that it is required. Humans learn skills through some combination of top-down instruction and interpretive execution. 1/
agreee that alphago needed its convolution layers. but connection to AGI not entirely obvious. what’s your argument?https://twitter.com/vdv7/status/950875282373775367 …
-
-
-
Through practice, this is "compiled" to reactive control. One view of deep RL is that we are trying to directly train a computer at the reactive level. While deep RL shows this can be done, it might never be useful for a general intelligence. fin/
- 1 more reply
New conversation -
-
-
because DeepMind say so? ;)
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.