91% of ML Models Degrade over Time

Re:91% of ML Models Degrade over Time by fenomas on Friday April 14, 2023 @10:11AM (#35569775)

> Can a machine with access only to statistical patterns in the distribution of text tokens infer the physical structure of reality? We can say, as certain as anything: No.

Um. How do you square that claim with the well-known Othello paper?

https://thegradient.pub/othello/

[ Parent | on HN ]

Re:91% of ML Models Degrade over Time by mjburgess on Friday April 14, 2023 @12:48PM (#35571651)

The board state can be phrased as moves. This paper profoundly misunderstands the problem.

The issue isn't that associative statistical models of domain Z aren't also models of domain Y where Y = f(Z) -- this is obvious.

Rather there are two problems, (1) the modal properties of these models arent right; and (2) they don't work where the target domain isn't just a rephrasing of the training domain.

[ Parent | on HN ]