----- Original Message ----- 
From: "Ben Goertzel" <[EMAIL PROTECTED]>

>snipped<

The Novamente approach involves learning representations of objects
learning a combination of supervised and unsupervised learning.

E.g. from seeing a lot of TV's in different situations, and used in
different contexts, the system will learn a whole bunch of overlapping
probabilistic rules for recognizing TV's.

So far we have not tested this process on real object perceived thru
real cameras though -- just on simple object in a simple sim world.

-- Ben


How noisy is the sim world, e.g. number of distractions, difficulty of
separating target object from ground? What types of variation can the target
objects show e.g. additional parts or deformation? Have you experimented
with identifying objects by their interactions in the simworld, not just
their appearance to simulated vision or touch?

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

Reply via email to