News for hackers. Stuff that matters.

A comment on Differentiable Genetic Programming (2016).

Re:Differentiable Genetic Programming (2016) by verdverm on Wednesday December 26, 2018 @09:00PM (#18766651)
I'm still facepalming GP because the associative and communative properties of algebra are omitted. Add in a nonlinear solver and you can reduce th problem size considerably.

http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.394....

[ Parent | on HN ]
Re:Differentiable Genetic Programming (2016) by joe_the_user on Friday December 28, 2018 @02:40PM (#18778903)
So do you mean that GP could sped-up by taking the evolutionary process it's simulating and using a solver to find the process' fixed-points?
[ Parent | on HN ]