Henrik Mettler
Henrik Mettler
In principle I agree, I quickly want to check in the literature though, whether there are case where this is disadvantageous
From Goldman and Punch 2014 (Analysis of Cartesian Genetic Programming’s Evolutionary Mechanisms): ```Compared on median evaluations to success, Normal and Reorder are likely to be equally good for simple problems,...
(CI-check fail seems like an unrelated mypy issue)
@mschmidt87 would be awesome if you find time to have a look, since you are the most knowledgeable of the Github actions CI :)
One question that arises, is whether we should also stop using the name `n_columns` and simply name it `n_hidden` since these things would become equal
yeah, i think I agree. Should we also remove `levels_back`? Atm I can't see any use case where anything but `levels_back=n_columns` is useful.
Atm the easiest way to deal with this is probably within the objective function, ie by penalizing such terms with a fitness penalty eg: ```python def objective(individual): f = individual.to_numpy()...
Looks very interesting, I need to have a closer look at the linked paper!