Well, many researchers understand this and are actively trying to build systems which has these inductive biases.https://twitter.com/GaryMarcus/status/1200646264150323200 …
-
Re: “mastering things without human knowledge” — progress in ML has always been about using human knowledge. These manifest as inductive biases — ConvNets, for instance, are built on the human intuition that objects of interest tend to be spatially clustered.
yes - but people sometimes title their papers otherwise. see my arxiv critique of AlphaZero https://arxiv.org/abs/1801.05667
-
-
Honestly, I'd be very surprised if any of the ten + 1 primitives you mention make controversial inductive biases (state of literature, 2019). Now are these primitives learnable from data? Perhaps some, but possibly at the cost of abysmal sample-complexity and insane compute.
-
i have never seen any of them learned robustly. ironically the great contribution of
@ylecun (arch-anti-nativist) was to figure out how to innately represent translation invariance in a neural network. way too inefficient (as you say) to learn it from a fully-connected system - 3 more replies
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.