Database approach to A.I.

new topic     » topic index » view thread      » older message » newer message

This is a multi-part message in MIME format.

------=_NextPart_000_0005_01C28687.25713BC0
	charset="iso-8859-1"

Hi all,
 Is anyone opposed to Mike Sabals method of creating the
a.i's foundational knowledge base,I must of missed it if
anyone disagreed--He said:


"I posit that the core of any AI project needs to be a=20
database
(probably EDS due to its flexibility) with which the program can store
information it learns about the people it interacts with. The program
will need to change its method of interaction based on the information
it gains. And as those people change and learn, the program needs to be
able to change its method of interaction along with them."


 I personally think its a sound approach from the programmer's =
standpoint,and it seems like the easiest
way to me.
  In addition,if you have noted the "guess the animal" program in the =
Euphoria demos section,that also seems
to be an simple way to have it learn things because it uses
a kind of pattern matching which might be able to be used
with in conjunction to neural nets which also do pattern
matching.
  Because if its going to learn,it has to remember,and having
a database that updates to hard disk is the only way I can
think for it to remember.Any suggestions?

------=_NextPart_000_0005_01C28687.25713BC0
Content-Type: text/html;
	charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable

<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META content=3D"text/html; charset=3Diso-8859-1" =
http-equiv=3DContent-Type>
<META content=3D"MSHTML 5.00.3315.2870" name=3DGENERATOR>
<STYLE></STYLE>
</HEAD>
<BODY bgColor=3D#ffffff>
<DIV><FONT face=3DArial size=3D2>Hi all,</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>&nbsp;Is anyone opposed to Mike Sabals =
method of=20
creating the</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>a.i's foundational knowledge base,I =
must of missed=20
it if</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>anyone disagreed--He said:</FONT></DIV>
<DIV><FONT face=3DArial size=3D2></FONT>&nbsp;</DIV>
<DIV><FONT face=3DArial size=3D2></FONT>&nbsp;</DIV>
<DIV><FONT face=3DArial size=3D2>"I posit that the core of any AI =
project needs to=20
be a </FONT></DIV>
<DIV><FONT face=3DArial size=3D2>database<BR>(probably EDS due to its =
flexibility)=20
with which the program can store<BR>information it learns about the =
people it=20
interacts with. The program<BR>will need to change its method of =
interaction=20
based on the information<BR>it gains. And as those people change and =
learn, the=20
program needs to be<BR>able to change its method of interaction along =
with=20
them."<BR><BR></FONT></DIV>
<DIV><FONT face=3DArial size=3D2>&nbsp;I personally think its a sound =
approach from=20
the programmer's standpoint,and it seems like the easiest</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>way to me.</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>&nbsp; In addition,if you have noted =
the "guess the=20
animal" program in the Euphoria demos section,that also =
seems</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>to be an simple way to have it learn =
things because=20
it uses</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>a kind of pattern matching which might =
be able to=20
be used</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>with in conjunction to neural nets =
which also do=20
pattern</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>matching.</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>&nbsp; Because if its going to learn,it =
has to=20
remember,and having</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>a database that updates to hard disk is =
the only=20
way I can</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>think for it to remember.Any=20

------=_NextPart_000_0005_01C28687.25713BC0--

new topic     » topic index » view thread      » older message » newer message

Search



Quick Links

User menu

Not signed in.

Misc Menu