News for hackers. Stuff that matters.

A comment on Learning Concepts with Energy Functions. Parent comment

Re:Learning Concepts with Energy Functions by jerf on Wednesday November 07, 2018 @04:35PM (#18402610)
With respect, no, that is not what it is. My summary is glib and phrased in non-mathematical terms, but closer.

A true Solomonoff Inductor would be wildly, wildly smarter than a human being, if it could get over the problem that such a machine would also consume super-exponentially more resources than the universe has.

[ Parent | on HN ]
Re:Learning Concepts with Energy Functions by yters on Wednesday November 07, 2018 @04:50PM (#18402707)
It's not a matter of resources. Solomonoff induction is not computable, since it needs to calculate the Kolmogorov complexity of the data.

If that is what is required for induction, it is surprising that humans are able to do so well at identifying concise descriptions of the data we observe. This seems inexplicable with a computational view of human cognition.

[ Parent | on HN ]
Re:Learning Concepts with Energy Functions by yters on Thursday November 08, 2018 @07:35AM (#18405812)
Disregard, I realized my error is that the elegant program is guaranteed to halt at some point, which gives us the Kolmogorov complexity. We just will never know when that happens, even with infinite resources.
[ Parent | on HN ]