Yann LeCun makes a very clear and honest statement of why Deep Learning is not enough. It's not enough because there are functions that don't emerge intrinsically from the network.https://twitter.com/ylecun/status/1215286749477384192 …
-
-
This Tweet is unavailable.
-
A small piece of code that runs in parallel with many others on a GPU.
- 2 more replies
-
-
-
Then I await someone pointing me to a concrete example of a non-ANN DL system.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Interesting. It seems difficult to model the spiking nature of the brain *without* parallelization. Real neurons operate in parallel as units in a distributed system.
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.