@chewxy Respectful disagree with DeepMind's Rich Sutton.
He is extrapolating from a past experience.
We might as well just use a very large k nearest neighbor search algorithm.
He is extrapolating from a past experience.
We might as well just use a very large k nearest neighbor search algorithm.
@chewxy The world is too complex for brute force.
Most of the methods coming out of research labs are not directly applicable to real world problems.
They normally get tested on toy datasets.
Most of the methods coming out of research labs are not directly applicable to real world problems.
They normally get tested on toy datasets.
@chewxy Most academic datasets don't capture the true variation of data in reality.
They are simplified.
Thus it would appear that brute force is working but it's not because the actual reality has so much variation that brute forcing is never going to be feasible.
They are simplified.
Thus it would appear that brute force is working but it's not because the actual reality has so much variation that brute forcing is never going to be feasible.
@chewxy Unless computational reasons are infinity.
@chewxy Even the human brain with 80+ billion neurons doesn't use brute force strategies.
@chewxy *resources
@chewxy Sorry disagree with that.
@chewxy Real world is orders of magnitude more complex with almost infinitely many states.
Brute forcing through that is impossible unless these people are telling me that computational power is going to keep ever increasing towards infinite without end.
Brute forcing through that is impossible unless these people are telling me that computational power is going to keep ever increasing towards infinite without end.
@chewxy The physical world wouldn't allow that, there is a limit to everything.
So that strategy can only go so far.
So that strategy can only go so far.
