Hi,

> I don't know if Novamente currently has such a PWM (perhaps by another
> name).  Anyway, my vision module has to interact with the PWM.  The main
> function of the vision module is to map the geon-based model to appearances.
>  I've had this part roughly figured out.
>
> Novamente's part is to help construct such a world model.  We need to find
> out how to represent objects, geons (which I can handle), and the
> interrelations between objects.  Let's avoid doing overlapping work...


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

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

Reply via email to