Interesting. I assume that OCR programmers already know about this.
On 13/03/2008, Linas Vepstas [EMAIL PROTECTED] wrote:
A bit of vision processing fun:
http://www.friends.hosted.pl/redrim/Reading_Test.jpg
--linas
---
agi
Archives:
On Thu, Mar 13, 2008 at 8:35 AM, Linas Vepstas [EMAIL PROTECTED] wrote:
A bit of vision processing fun:
http://www.friends.hosted.pl/redrim/Reading_Test.jpg
Interesting: is it possible to construct similar thing in audio form?
It'll have to preserve some sequences of sounds, because we learn
On 14/02/2008, Mike Tintner [EMAIL PROTECTED] wrote:
Pei: Though many people assume reasoning can only been applied to
symbolic or linguistic materials, I'm not convinced yet, nor that
there is really a separate imaginative reasoning --- at least I
haven't seen a concrete proposal on
On 13/03/2008, Linas Vepstas [EMAIL PROTECTED] wrote:
object itself. How, say, do you get from a human face to the distorted
portraits of Modigliani, Picasso, Francis Bacon, Scarfe, or any
cartoonist?
By logical or mathematical formulae?
Actually, yes. Computer vision processing
On 13/03/2008, Vladimir Nesov [EMAIL PROTECTED] wrote:
On Thu, Mar 13, 2008 at 8:35 AM, Linas Vepstas [EMAIL PROTECTED] wrote:
A bit of vision processing fun:
http://www.friends.hosted.pl/redrim/Reading_Test.jpg
Interesting: is it possible to construct similar thing in audio form?
On 13/03/2008, Bob Mottram [EMAIL PROTECTED] wrote:
Interesting. I assume that OCR programmers already know about this.
Traditional OCR tries to recognize one letter at a time, together
with guidance from a spell checker. For this example, the spell
checker would barf, so OCR might get all the
Here is an article about RPI's attempt to pass a slightly modified version
of the turning test using supercomputers to power their Rascals AI
algorithm.
http://www.eetimes.com/news/latest/showArticle.jhtml?articleID=206903246pri
ntable=true
The one thing I didn't understand was that they said
One thing worth noticing is that it looks like this effect only works
provided that words with three letters or fewer are not garbled. I
think what this shows is that there is a statistical element to
reading. So provided that the beginning and ending characters are
correct, and what's in
Thanks for the info, Ben
Ed Porter
-Original Message-
From: Ben Goertzel [mailto:[EMAIL PROTECTED]
Sent: Thursday, March 13, 2008 10:38 AM
To: agi@v2.listbox.com
Subject: Re: [agi]
I know Selmer and his group pretty well...
It is well done stuff, but it is purely
So Ben, based on what you are saying, you fully expect them to fail their
Turing test?
Eric B. Ramsay
Ben Goertzel [EMAIL PROTECTED] wrote: I know Selmer and his group pretty
well...
It is well done stuff, but it is purely hard-coded-knowledge-based
logical inference --
there is no real
If the test is defined to refer ONLY to conversations about
a sufficiently narrow domain of objects in
a toy virtual world ... and they encode enough knowledge ... then maybe they
could brute-force past the test... after all there is not that much to
say about
a desk, a table, a lamp and a box ...
You don't have a goal of self preservation. You have goals like eating,
breathing, avoiding pain, etc. that increase the odds of passing on your
genes.
Wrong. I most certainly *DO* have a goal of self-preservation. Even if it
is quick and utterly painless, I do *NOT* want to die.
Why do
--- Mark Waser [EMAIL PROTECTED] wrote:
You don't have a goal of self preservation. You have goals like eating,
breathing, avoiding pain, etc. that increase the odds of passing on your
genes.
Wrong. I most certainly *DO* have a goal of self-preservation. Even if it
is quick and
If there are competing groups of agents, then evolution will favor goals
that
promote survival of the group (for example, self sacrifice). If there is
only
one group, then this evolution does not occur.
Why not? The agents are competing with the environment (not each other)
and will
I *very* rarely cross-post but felt that cross-posting the following that I
just placed on the SL4 list to here was the Friendliest way to fulfill my
promise of attempting to ensure that any salient points make it to both
lists.
From: Rolf Nelson
Here's some generic unsolicited advice
I reckon that the shuffled words (meaningless and low probability) trigger
an internal representation that is close enough to the meaning_full_
representation to be correctly classified.
One part of this triggered internal representation is about WHAT is present,
the other part about WHERE these
--- Mark Waser [EMAIL PROTECTED] wrote:
If there are competing groups of agents, then evolution will favor goals
that
promote survival of the group (for example, self sacrifice). If there is
only
one group, then this evolution does not occur.
Why not? The agents are competing
17 matches
Mail list logo