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?
evans and @egrefen is also a arguably a hybrid of a different sort that is demonstrably better than #deeplearning alone. and recent work by Kolhi/Tenenbaum and others also qualifies, to name a few
-
-
It's true,
@LittleBimble and I are, in fact, human-robot hybrids. We prefer the term "cyborg", personally, but we accept it takes time for society to adjust. -
ha ha. i was referring to your paper, but i do think all humans have hybrid architectures.
- 1 more reply
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.