learning with constraints
- From: "JGCASEY" <jgkjcasey@xxxxxxxxxxxx>
- Date: 26 Nov 2005 16:42:44 -0800
>>From earlier thread in comp.ai.philosophy
From: "Glen M. Sizemore"
Date: Thu, 24 Nov 2005 12:36:47 -0500
Local: Fri, Nov 25 2005 4:36 am
Subject: Re: Cool visual illusion
JC:
I suspect we can learn just by being
exposed to an input with constraint as an
automatic result of the way we are wired.
GS:
I'm sorry, this sounds like gibberish.
Is that deliberate?
What I was thinking of was the acquisition
of knowledge. For example a favorite beginner
text processing program is to count the
frequency of each character in a text string.
Then to count how frequently one character
is followed by another.
Thus we can say the program has *learnt* how
frequently each character occurs and has
*learnt* how often each character is followed
by each other character.
This learning is the result of how the system
(computer) is wired (program) and being given
(exposed to) an input with constraint. An input
without constraint would make every character
and sequence of characters equally likely and
therefore what would there be to learn?
There is no reward system involved, it is just
the consequence of the wiring (program) and
the type of input (non random).
--
John Casey
.
- Follow-Ups:
- Re: learning with constraints
- From: Glen M. Sizemore
- Re: learning with constraints
- Prev by Date: Re: Cool visual illusion
- Next by Date: Re: Cool visual illusion
- Previous by thread: new film on consciousness
- Next by thread: Re: learning with constraints
- Index(es):
Relevant Pages
|