From: Justin Corwin (thesweetestdream@hotmail.com)
Date: Sun May 19 2002 - 16:42:35 MDT
>From: "Michael Roy Ames" <michaelroyames@hotmail.com>
>Your note (admittedly hastily typed) seems to meld/mix-up/confuse(?) two
>concepts: an Artificial Environment, and a Sensory Modality>
<snip>
Well, er. sort of. See, I'm referring to Environment mostly from a design
perspective. So environment is whatever we design the AI to relate to. So
this necesarily implies sensory modalities, visual corticies, etc. it also
implies, a sim world, or cameras, and lots of other stuff, but I was trying
to KISS in order to explore the concepts.
>I think you missed this important reason:
>
> 5. To ground concepts in physical reality. (Or a physical reality
>simulation).
>
>Although your item 4. seems to infer this, I suspect that grounding is an
>essential requirement for stable mental development, almost from the start
>of a Baby AI's existence. Here are two arguments to support that view:
I think you're right. However, I believe that to be a subset of my #2.
action/response training.
The question is, how important is experimentation in providing experience?
We equate physically doing things with high importance because we can't gain
experience well from other peoples efforts. however, an AI may be able to
learn as if it were doing the experiment it's reading about. So physically
doing things may decrease in importance.
>
<snip good arguments for human-like AI having human environment>
after this point, we seem to agree. Thanks for your comments and insightful
response!
Justin Corwin
"and all who listen will hold his manhood cheap, that he was not here, on
this day, by my side, on st. crispin's day"
~"c'mon, do I have to tell you everything?"
_________________________________________________________________
Chat with friends online, try MSN Messenger: http://messenger.msn.com
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:38 MDT