These terms need to be used carefully...
Evolutionary algorithms, as a learning technique, are sometimes a good
solution ... though in NM we don't use any classical evolutionary
algorithms, relying instead on a customized version of MOSES (see
www.metacog.org for a description of the general approach and the
Boolean-function version ... in NM we require a much more general
version), which combines evolutionary-learning ideas with probabilistic
analysis and rule-based program normalization.
However, using evolutionary algorithms within an AI architecture, for
specific purposes, is totally different from using evolutionary
algorithms to CREATE one's AI architecture...
The latter, I agree, is "the last game in town" ...
-- Ben
Peter Voss wrote:
Evolutionary approaches are what you use when you run of engineering
ideas... (and run of statistical approaches)
The last game in town.
Some of us are making good progress towards AGI via engineering.
Peter
-----Original Message-----
From: Eugen Leitl [mailto:[EMAIL PROTECTED]
Sent: Monday, March 12, 2007 1:43 PM
To: Russell Wallace; agi@v2.listbox.com
Subject: Re: [agi] Logical representation
On Mon, Mar 12, 2007 at 07:47:26PM +0000, Russell Wallace wrote:
...
The first and biggest step is to get your system to learn how to evolve.
I understand many do not yet see this as a problem at all.
shot at that route, let me know if you want a summary of conclusions
and ideas I got to before I moved away from it.
I don't understand why you moved away from it (it's the only game
in town), but if you have a document of your conclusions to share,
fire away.
-----
This list is sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/?list_id=303
