I recently challenged Hinton and @YLecun to stand by the idea expressed in these words from their 2015 Nature paper, by making a public bet. Neither would. I stand by my assertion that is precisely this that holds back deep learning, except brave work by people like @egrefen.https://twitter.com/MLWave/status/1065310317935304704 …
-
Hm, I haven’t seen or heard that talk, but I agree that this is what it sounds like. Nonetheless, I don’t believe there’s a clean cleft between symbolic systems and connectionism, and as such I think a lot of DL research reintroduces such concepts without calling them as such.
“The fathers of AI believed that...human reasoning must...[have] rules of inference containing variables that got bound to symbols...this belief is...incorrect as the belief that a lightwave can only travel through space by causing disturbances in the luminiferous aether” -Hinton
-
-
Right. Yet one of the motivations for capsule networks is encoding the fact e.g. that spatial transformations preserve spatial relationships, i.e. that there is an object in the image, and that it’s still the same when seen from a different viewpoint. Symbols creeping back in…
-
So would he still stand by those words? I don’t know. We could ask him...
- 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.