Tim Hanson on Nostr: npub14d70x…zdm4s npub1qtkdu…txqrw imho: Scientific models are a bit different ...
npub14d70xk632yuqshz7hdrnnj79j3yufrphy4u7ryekmpr7vztwvf5q8zdm4s (npub14d7…dm4s) npub1qtkdu9s8mnygvkcvycw0wtmp85t95v25v8eyavtkx2q0nhnuxmnq9txqrw (npub1qtk…xqrw)
imho: Scientific models are a bit different than ML models -- they are closer to generator programs than to classifiers or function approximators.
If theories are closer to programs, they are better defined by Kolmogorov complexity; classifiers and function approximators are better defined (as mentioned) by VC dimension or Rademacher complexity...
Theories also call each other recursively, like Maxwell's equations; another reason to consider them 'programs'.
imho: Scientific models are a bit different than ML models -- they are closer to generator programs than to classifiers or function approximators.
If theories are closer to programs, they are better defined by Kolmogorov complexity; classifiers and function approximators are better defined (as mentioned) by VC dimension or Rademacher complexity...
Theories also call each other recursively, like Maxwell's equations; another reason to consider them 'programs'.