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 …
-
-
I guess all you folks truly believe that intelligence lies in control system but not the whole body. So, the body evolved to accomodate a complex brain and discovering the right control system architecture is all about building intelligent machines. Good luck guys...
-
Don't be so smug thinking we don't realize the importance of biological evolution. I've been writing about that extensively. What have you written?
- 6 more replies
New conversation -
-
-
So, DL is an architecture AND a methodology AND the mechanism behind all of evolution? Next, you’ll tell me that is also serves to unify the theory of gravity with the standard model of physics!
@GaryMarcus -
No, my understanding is that Yann LeCun thinks of DL as automating the optimization of a program for computing a complex function. Depending on the optimization method, the program or its generator function will often be differentiable.
- 9 more replies
New conversation -
-
-
I think I'm accurate in describing what he said. He used the word 'instantiated' in the sense that it was an initial condition to get the machinery running. These conditions, don't arise from the machinery.
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.