> I like the idea of using a fundamentally time-savvy representation, and a
> vector-based representation does that...
> 
> This is one of the stronger points in Jeff Hawkins' recent book "On
> Intelligence" -- he reviews in detail how most human perception, including
> visual perception, is fundamentally time-based and based on temporal pattern
> recognition.
> 
> -- Ben

Can you explain a bit what is meant by 'vector'? Any high-dimensional
datum can be regarded as a vector, or do you mean something specifically
temporal?

Also, I think visualization would be a difficult problem in "show and
tell", because humans are not good at grasping high-dimensional data.
It seems that translating to the pixel level is the only way...

YKY

PS. I've talked to SmartRobot.com, and they say they're interested in
the visual recognition module. I asked them if they'll be interested
in touch, proprioception, and sound as well. But I'm wondering if
there are other robotics companies who will do those things.

-- 
_______________________________________________
Find what you are looking for with the Lycos Yellow Pages
http://r.lycos.com/r/yp_emailfooter/http://yellowpages.lycos.com/default.asp?SRC=lycos10

-------
To unsubscribe, change your address, or temporarily deactivate your subscription, 
please go to http://v2.listbox.com/member/[EMAIL PROTECTED]

Reply via email to