ANNEvolve :: Evolution of Artificial Neural Networks

There is a well known idea that if you could put billions of monkeys onto billions of typewriters, and keep them typing away, then eventually, just by chance, they would produce the complete works of Shakespeare.

Now that has always struck me as a cute idea, but not true, because I estimate the probability of turning out several thousand characters in a specific order is vanishingly small, and would therefore require more monkeys and typewriters than there are atoms in the universe. (I have not actually made that calculation, however.)

Of course there are other difficulties which make that project impossible anyway, such as the difficulty of getting the monkeys to cooperate, where to put all those typewriters, how to feed them all, and how to get rid of all the monkey poop. You would also have to have computers scanning all the output and comparing them with the known works of Shakespeare to see if they actually did it. Hence it has always been clear to me that this is just a fantasy.

But recently I had the thunderous realization that this experiment has already actually been performed! And what is more, the monkeys succeeded, eventually producing the complete works of Shakespeare! Furthermore, the typewriters were not even necessary. The monkeys fed themselves and took care of their own housekeeping. They mostly had fun performing this experiment, even though it took many millions of years. Their primary tools were their reproductive organs, which they generally enjoy using.

By now, dear reader, you have probably figured out that I'm referring to the process of evolution, acting on the primates of 100 million years ago. To call them monkeys is not exactly accurate; they were the precursors of today's apes, monkey, and humans. But one of their descendants, all by himself, produced the complete works of Shakespeare. He was, of course, William Shakespeare.

Soon afterwards, the same process produced the typewriter!

How Simulated Evolution Works

Author: Mitchell Timin
Posted: 11/16/2003

Meet Annevolve's skydiving, mouseball collecting Unix Admin

Author: Eric Anderson
Posted: 11/14/2003

Species Learning and a Hypothesis About Brain Learning

Author: Mitchell Timin
Posted: 10/02/2003

When doing GA, expect a very large variance in the time required to accomplish a certain amount of evolution.

Author: Kent Pault Dolan
Posted: 09/09/2003

An Aspect of Natural Evolution

Author: Mitchell Timin
Posted: 08/31/2003

Genuine Artificial Intelligence :)

Author: Mitchell Timin
Posted: 08/27/2003