For long, I’ve been dreaming of making a small world (on a computer) where I can experiment with evolution. Too ambitious? Perhaps. We already know that order and complexity can emerge from simple ingredients (e.g. cellular automaton). How about intelligence? Will it emerge out of simple rules?
To be more specific, I want to make a slightly complicated version of a cellular automaton with a little more realistic life-like entities. I’d like to make an environment in which lives can think, act, learn, reproduce, and die. Changes caused by reproduction will make diversity of the lives, and natural selection would keep the entities that fit the current environment. The process goes on and in the end, in an ideal scenario that I’m dreaming of, progressively intelligent entities would emerge from such an environment.
I know this project will not be very easy. Probably many people had already tried and failed. Can I contribute at all by doing it as a hobby? I don’t know. Will I have a unique perspective to tackle this issue? Maybe. Even if I won’t achieve much, but it’s fine. I’ll learn something valuable through the process (at the very least, more programming skills).
There are two important factors for this. The first one is the genetic algorithm implemented by inheritance and natural selection. I won’t use a specific training function, but let them survive in the environment. If they thrive, they survive. The second one is neural networks whose structure can be changed through evolution and can be trained through the course of a single life.
Articles that I will write in this blog will be like a journal for this exploration. In each article, I’ll focus on a small topic. Let’s see how it goes. I’m excited.
