I really liked colormind.io, and made a little toy Vue site when I was looking for a job (I grabbed your colors and pushed them to state so my website colors changed). See here: http://q8z8p.net/#/color. I just wanted to thank you because I think that was helpful in getting my first job!
Thanks for the reply, I dove a bit more into it after making this comment and read some of the pages on your site discussing the process and practical application. Really interesting stuff and I appreciate the effort going into explaining it all. I guess I underestimated the depth of the problem space. Even while writing my comment I got to thinking about how colour theory would account for subjectivity and outlying pallettes that work well but don't have obvious relationships between vibrant colours.
That got me wondering if the process going on for colourmind could be turned into a new theory on colour. Is there a way to boil the process down into a deterministic one, or do you feel like the neural network is accomplishing something that couldn't be refined into a "rule" or guidline to use in a regular theory?
it's hard to say because GANs are still black boxes. There's a lot of research into explainable ANNs that gives some explanation as to how the NN arrived at a particular conclusion, so I think it should be possible in the future.
as an experiment, try this:
go on https://color.adobe.com and click on one of the color rules (it will give you a random palette based on the rule)
now compare with a palette from https://coolors.co/ or https://color.adobe.com/explore/ (user-uploaded)
if color theory + regression fully solved this problem, none of these color sites would need to exist.