I wonder if anyone has attempted to use machine learning to try and build a better paper airplane. I feel like that would be super interesting.
Making it bigger doesn't "just work"... same for the inverse.
This approach works well for real planes since 99.999% of them use standard NACA airfoils that are well documented in the public domain.
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.648...