ok!
- Original Message -
From: Samantha Atkins [EMAIL PROTECTED]
To: agi@v2.listbox.com
Sent: Wednesday, July 05, 2006 9:47 PM
Subject: [agi] ping
No mail seen since 6/30. Testing.
---
To unsubscribe, change your address, or temporarily deactivate your
subscription,
please go
What are the measurable fitness functions that can be built into AI?
Dan Goe
- Original Message -
From: William Pearson [EMAIL PROTECTED]
To: agi@v2.listbox.com
Sent: Thursday, July 06, 2006 5:21 AM
Subject: Re: [agi] Flow charts? Source Code? .. Computing Intelligence? How
too?
On Thu, Jul 06, 2006 at 10:28:57AM -0400, Danny G. Goe wrote:
What are the measurable fitness functions that can be built into AI?
You don't seem to be really communicating, only going through the motions.
--
Eugen* Leitl a href=http://leitl.org;leitl/a http://leitl.org
I am new to AI.
Just trying to draw on the knowledge to see what has been done and can be
done, to better understand the developing technology.
I do believe the fitness function(s) key to directing AI evolution.
Dan Goe
From : Eugen Leitl
Measures of fitness used to optimise systems can be many and varied. In an application where a mobile robot needs to navigate from one location to another using its sensors you can use measures such as:- the number and type of features detected within the robot's vacinity
- amount of time to make
I am new to AI.
If you're new to AI, then you should be reading the general literature
and getting yourself up to speed, not asking particular general questions
whose answers can't be understood unless you have the necessary base of
knowledge. The reason why virtually no one is
Thanks, Russell.
From : Russell Wallace [EMAIL PROTECTED]
To : agi@v2.listbox.com
Subject : Re: [agi] Measuerabel Fitness Functions? Flow charts?
Source Code? .. Computing Intelligence? How too? . ping
Date : Thu, 6 Jul
On 06/07/06, Russell Wallace [EMAIL PROTECTED] wrote:
On 7/6/06, William Pearson [EMAIL PROTECTED] wrote:
How would you define the sorts of tasks humans are designed to carry
out? I can't see an easy way of categorising all the problems
individual humans have shown there worth at, such as
If you're that focused on fitness functions, why not define it as the core of
intelligence? Make an AI focused on evolving fitness functions for itself...
without anything else, it might be an empty definition, but if you insert some
other, trivial fitness criteria, such as maze navigation with
On 7/6/06, William Pearson [EMAIL PROTECTED] wrote:
This is an interesting term. If we could define what it meansprecisely we would be a long way to building a useful system. What doyou think the closest system humanity has created to a pgpps is?
The Internet.
Ageneric PC almost fulfils the
10 matches
Mail list logo
