News for hackers. Stuff that matters.

A comment on Deep symbolic regression for recurrent sequences.

Re:Deep symbolic regression for recurrent sequences by not2b on Sunday January 30, 2022 @05:15PM (#30141741)
Doesn't do well with 2,3,5,7,11,13. Perhaps they can figure out how to incorporate OEIS or a similar resource in addition to just a simple curve fit.
[ Parent | on HN ]
Re:Deep symbolic regression for recurrent sequences by CasperDern on Sunday January 30, 2022 @08:00PM (#30143127)
The goal of the paper was not to get the best pattern fitter, but to see if it's even possible to do symbolic regression with a simple token-to-token prediction method.
[ Parent | on HN ]
Re:Deep symbolic regression for recurrent sequences by somebodythere on Sunday January 30, 2022 @05:20PM (#30141789)
That sequence is out of domain I think.
[ Parent | on HN ]
Re:Deep symbolic regression for recurrent sequences by alar44 on Monday January 31, 2022 @12:54AM (#30145051)
Lol, beat me to it.
[ Parent | on HN ]