Machine Learnability as a Measure of Order in Aperiodic Sequences

Re:Machine Learnability as a Measure of Order in Aperiodic S... by muhdeeb on Sunday October 05, 2025 @02:40AM (#45479352)

Huh. That's an interesting possible metric. How many competing tendencies in a space? It a good question and one that's been asked before.

I wonder how machine learnability compares to other measures of chaotic structure, like multi-fractal approaches etc. I wouldn't be that surprised if it's accidentally the same or quite similar to some of the existing metrics.

[ Parent | on HN ]

Re:Machine Learnability as a Measure of Order in Aperiodic S... by soulofmischief on Sunday October 05, 2025 @03:18AM (#45479534)

I think it's pretty obvious that the amount of order/entropy in a system corresponds to the amount of knowledge contained in / that can be able extracted from a system. This is a fundamental aspect of information theory.

[ Parent | on HN ]

Re:Machine Learnability as a Measure of Order in Aperiodic S... by Y_Y on Sunday October 05, 2025 @03:52AM (#45479716)

One mans' "pretty obvious" is another's "true by definition". It's not a "fundamental aspect" so much as it's just what those words mean.

[ Parent | on HN ]

Re:Machine Learnability as a Measure of Order in Aperiodic S... by soulofmischief on Sunday October 05, 2025 @04:28AM (#45479922)

Yes, that's a tighter way of saying it :)

[ Parent | on HN ]