What really is at stake in current debates about deep learning & AI? A reply to #deeplearning pioneer Yoshua Bengio.https://link.medium.com/pFZy4GfpJ0
-
if you're not advocating for a "simple hybrid" between symbolism & connectionism, then can you please point to a single implementation that: a) is representative of the thing you have in mind, and b) succeeded on a challenging task that has escaped a pure DL system?
as i have explained before AlphaGo is actually a great example: monte carlo tree search plus deep learning. since i heard you read the book, am surprised you missed this.
-
-
You think the solution is hidden layers we can’t explain? maybe if the monte carlo tree search is built by the AGI.
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.