Replies

If you truly are curious... come back when Scientific American's website is up and get their referred works from that article and run these papers through an university library.

I'm actually curious enough to read the stuff. That is why I know they have no evidence. I read the thing here---Evolving Inventions

You will note they have no references for the experiments. What references are there give him a little spending money (except for the Turing ref)


Computing Machinery and Intelligence. Alan M. Turing in Mind, Vol. 59, No. 236, pages 433–460;
October 1950. Available at www.abelard.org/turpap/turpap.htm by permission of Oxford
University Press.
Genetic Programming: On the Programming of Computers by Means of Natural Selection.
John R. Koza. MIT Press, 1992.
Genetic Programming: The Movie. John R. Koza and James P. Rice. MIT Press, 1992.
Genetic Programming III: Darwinian Invention and Problem Solving. John R. Koza, Forrest H
Bennett III, David Andre and Martin A. Keane. Morgan Kaufmann, 1999.
Genetic Programming III: Videotape: Human-Competitive Machine Intelligence. John R. Koza,
Forrest H Bennett III, David Andre, Martin A. Keane and Scott Brave. Morgan Kaufmann, 1999.
Genetic Programming IV: Routine Human-Competitive Machine Intelligence. John R. Koza,
Martin A. Keane, Matthew J. Streeter, William Mydlowec, Jessen Yu and Guido Lanza.
Kluwer Academic Publishers (in press).

These are not references. These are "More to Explore".

From the same authors... I don't think it's the same amazing circuit talked about here on FR, but nonetheless working circuits resulting from a genetic algorithms. Evolution using genetic programming of a low-distortion, 96 decibel operational amplifier

You said that they had nothing, you basically said that GAs were all untrue. Those results are not nothing. I've not done any actual research with GAs, but I can tell you that they're pretty amazing in their capabilities... when you want to know about NNs and PR stuff, gimme a call.

Since I know that you'll (1) want the original 9-transistor circuit next, (2) after that, you'll want a genetic algorithm besting Xeons, I'll end my discussion here. It's fairly easy to do an university-library search on the authors' names (which is what I did on one author's name), track down their university websites and e-mail them, et cetera if you want to.