Out of curiosity, does anyone know of examples where genetic algorithms are the "right choice"?
I thought they were really nifty when I first heard of them, but thinking of them as an optimization procedure, they don't really stand up in my experience to basic gradient descent methods. Sure, you can e.g. train a neural network with genetic algorithms, but why would you?
I thought they were really nifty when I first heard of them, but thinking of them as an optimization procedure, they don't really stand up in my experience to basic gradient descent methods. Sure, you can e.g. train a neural network with genetic algorithms, but why would you?
I'd love to be proven wrong though :)