Re:Machine Learning’s ‘Amazing’ Ability to Predict Chaos
by evrydayhustling on Thursday April 19, 2018 @06:57AM
(#16874804)
This interpretation sounds right to me. I found it cool that the article characterizes success in terms of prediction accuracy out to N "Lyapunov times", a concept that is supposed to incorporate the unpredictability of the system. So perhaps discovering these regularities proves that in this implementation, the true Lyapunov time is longer.
Surely they're discovering hidden (or obvious) regularities based specifically on the process being deterministic.
As a counter example, the Smale Horseshoe [1] is an example of a inherently unpredictable map - it's approximately equivalent to choosing a real number "at random" and attempting to "predict" each digit as you find it. Sure, if some implementation has chosen a number with repeating digits, you can "predict" those digits but this would have nothing to do with being an oracle for algorithm itself.
More broadly, I think it's pretty established that any realistic model of weather is kind of an extension of this concept - it depends unstably on it's initial conditions (small changes in initial conditions result in large changes in final result after some period).
[1] https://en.wikipedia.org/wiki/Horseshoe_map