About the Meta-evolver

Author:  Mitchell Timin
Posted:  06/11/2006

Driftwood :: Harnessing the Power of Many Computers for Simulated Evolution

Author:  Mitchell Timin
Posted:  03/21/2004

Meet ANNEvolve's founder and leader

Author:  Mitchell Timin
Posted:  02/16/2004

4-Play Procedure Analysis

Author:  Mr. Emile Richard
Posted:  01/23/2004

Shakespeare, Darwin, and the Monkeys

Author:  Mitchell Timin
Posted:  12/26/2003

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

Currently, my software falls within the realm of AI, but I don't kid myself that my programs have any kind of real intelligence. Depending on one's definition of "artificial intelligence", my programs might have some. They do learn. The learning is similar to the "species learning" that is most obvious in ants and bees. Although individual ants and bees don't learn very much, the evolving population of any particular species has learned a great deal. But this kind of learning is very different from what we do, or at least seems to be very different. Possibly there is evolution going on within our personal neural networks, so maybe the difference is not as profound as it seems. What I mean by that is that it's possible that there is an evolutionary process going on within our brains, pitting sub-populations of neurons against each other. Since the brain has many billions of neurons it could easily set 1000 groups of 1000 neurons to compete against each other. Each group of 1000 would be a neural network, but every group would be a little different, both in the topology and strength of their synaptic connections. Each group is like a team competing in a sports event. Those that performed poorly would be rewired, partially imitating those that did well. Eventually, one of these neuronal "teams" would become a permanent feature of this brain's wiring. The others return to the pool of neurons. (I'm hypothesizing that the brain maintains a huge pool of available neurons for many purposes.) All of this is rampant speculation on my part. But I think its a legitimate, and potentially testable hypothesis, that short term evolution proceeds within the brain, based on Darwinian competition between groups of neurons. The losers don't have to die of course, they can be reused.

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