Re: Hawkins ideas on building AI's
From: Eray Ozkural exa (examachine_at_gmail.com)
Date: 10/25/04
- Next message: The Sophist: "Re: Three Dog Problems"
- Previous message: dan michaels: "Re: Three Dog Problems"
- In reply to: bkaz: "Re: Hawkins ideas on building AI's"
- Next in thread: bkaz: "Re: Hawkins ideas on building AI's"
- Reply: bkaz: "Re: Hawkins ideas on building AI's"
- Reply: dan michaels: "Re: Hawkins ideas on building AI's"
- Reply: bkaz: "Re: Hawkins ideas on building AI's"
- Messages sorted by: [ date ] [ thread ]
Date: 25 Oct 2004 16:10:54 -0700
bkaz_@hotmail.com (bkaz) wrote in message news:<def186b4.0410250435.67a0eec7@posting.google.com>...
> > I'm not quite sure why you say abstraction is the only way to predict
> > the future. However, since the memory-prediction system needs to
> > generalize, it helps to send data to it which is abstracted already.
> > Every real image is slightly or greatly different from the others, so
> > the common features are what's important.
>
> My 2c: abstaction, generalization, & pattern recognition is the same
> process,- discovery of common (invariant) features. Generality is
> range*precision of the commonality, what I call accumulated match,
> which is the only possible predictor of future match (a quantifier of
> induction). Again, many different words that really mean the same
> thing.
Same process, might be. But you are simply substituting "pattern" with
"feature". Just what is a pattern? What is a feature? What use is this
whole process?
Regards,
-- Eray
- Next message: The Sophist: "Re: Three Dog Problems"
- Previous message: dan michaels: "Re: Three Dog Problems"
- In reply to: bkaz: "Re: Hawkins ideas on building AI's"
- Next in thread: bkaz: "Re: Hawkins ideas on building AI's"
- Reply: bkaz: "Re: Hawkins ideas on building AI's"
- Reply: dan michaels: "Re: Hawkins ideas on building AI's"
- Reply: bkaz: "Re: Hawkins ideas on building AI's"
- Messages sorted by: [ date ] [ thread ]
Relevant Pages
|