Huge thanks to the wonderful folks at Kaggle who worked on this! :)
-
-
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
ARC is a set of IQ-like tasks that: 1) don't reuse knowledge other than "Core Knowledge" (basic set of knowledge primitives that even v. young children possess) 2) Are readily solvable by humans, without training or instructions 3) Are out of reach for current AI... or are they?
Show this thread -
I hope this challenge will help the rise of alternative approaches to program synthesis that leverage human cognitive priors & focus on abstraction & generalization -- instead of the usual "learn the manifold of the data using a dense sampling of it, then do local interpolation".
Show this thread
End of conversation
New conversation -
-
-
Looking at just the few training examples and ruminating, every solution I can think is devolves to just a graph search so far... gonna be interesting to see what People come up with here
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This may be the only dataset and competition that the results would serve as a step for explaining intelligence and to general artificial intelligence.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks F! Amazing challenge. This weekend I start. The most interesting problem (problems) I have seen in a long, long time.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
a program able to solve these tasks with that little trainingdata is way more worth than 20k imo. thats basicly general intelligence.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Wow this looks very similar to a project I did last year! I generated some easy rules similar to conway's game of life and checked how the network could learn such rules: https://github.com/evinpinar/Conway-s-Neural-Life … But of course, this was an extremely simplistic, few days experiment :)
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
It's really a big competition. It's based on Chollet’s paper on measuring intelligence organised at
@MIT. Good luck for the participants.Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.