Gary Marcus Retweeted Yann LeCun
good question here from @ylecun (though I would perhaps seek to “supplement” rather than “replace”); great if others would weigh inhttps://twitter.com/ylecun/status/1071695437835440128 …
Gary Marcus added,
Yann LeCun @ylecun
Replying to @GaryMarcus @tdietterich @andrey_kurenkov
DL = { models are modular & non-linear, minimizes an objective function, computes gradient "analytically", uses gradients to minimize }.
(This applies to all learning paradigms: supervised, unsupervised,...)
Which of these 4 pillars do you propose to replace, and by what?
8:28 AM - 9 Dec 2018
0 replies
0 retweets
4 likes
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.