Evolution of Mona Lisa Via Genetic Programming

mhelander writes "In his weblog Roger Alsing describes how he used genetic programming to arrive at a remarkably good approximation of Mona Lisa using only 50 semi-transparent polygons. His blog entry includes a set of pictures that let you see how 'Poly Lisa' evolved over roughly a million generations. Both beautiful to look at and a striking way to get a feel for the power of evolutionary algorithms."

Comments

There is nothing evolutionary about this...

[tjwhaynes]

This isn't an example of evolution in action; this is closer to a simulated annealing because there is a set goal - make a set of transparent polygons look like the target image. Mutate-and-iterate is not enough to make this evolutionary.

Evolution does not have a stringent end-goal - there is no finish line, and no qualification of perfection. Evolutionary algorithms must merely out-compete their peers and survive for the next round.

That doesn't make the article bad - the idea is interesting and the results are impressive. However, whoever titled this Evolution is clearly confused.

Cheers,
Toby Haynes