You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
One interesting thing about the ARC competition is that it serves to highlight how people who use deep learning often have little idea of what deep learning actually does, and when they should be using it or not
DL is applicable when you're doing *pattern recognition*: when you have data that lies on a smooth manifold, along which samples can be interpolated. And you're going to need a dense sampling of your manifold as training data in order to fit a parametric approximation of it
Generalization in deep learning is interpolation along a latent manifold (or rather a learned approximation of it). It has little to do with your model itself and everything to do with the natural organization of your data
Differentiability & minibatch SGD are the strengths of DL: besides making the learning practically tractable, the smoothness & continuity of the function & the incrementality of its fitting work great to learn to approximate latent manifold. But its strengths are also its limits
The whole setup breaks down when you are no longer doing pattern recognition -- when you no longer have a latent manifold (any kind of discrete problem) or no longer have a dense sampling of it. Or when your manifold changes over time.
This is indeed, and unfortunately, a sign of the current status of ML as a research field. I frankly can't imagine how to employ deep learning for ARC (at least in a way that makes sense and that is coherent with the expectations of your paper "On the measure of Intelligence").
It might be a good thing. Sometimes we can see unexpected surprises from being “foolish”
This is not about "following the rules" or breaking them, this is about understanding what you are doing. Being clueless is not the same as being creative.
From what little knowledge of ML/DL I have, I don't think this problem is completely solvable by computers. But yes I understand what real intelligence is like.
The ARC competition is a great way to realize how impressive the human brain is and how little we know about intelligence.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
