On Wed, Jan 15, 2014 at 7:29 PM, Russell Wallace
<[email protected]>wrote:

> I saw your post. I don't have an opinion about the geometry of mind, but
> you're still on the list :)
>


Thanks =)  Well, to explain why we're interested in the geometry of
mind...

In logic-based AGI, the KB is a collection of logic formulas.  We may try
to organize this KB with a hierarchical (ie, tree) structure, somewhat akin
to a library catalog of books.  That is more or less standard classical AI
stuff (although I'd argue that no one has yet built such a complete system
with all the ingredients right).

The geometry of mind concerns what happens when we try to map the logic
formulas into a mathematical "space".  That has more meaning than a mere
collection of formulas (ie, a set).  If the set has "neighborhoods", we
have a topology.  If this topology has a distance metric, then we have a
"geometry".  If the distances varies continuously, we have a differential
geometry (or "manifold").

Knowing the spatial structure of the "mind" (ie the KB), may present new
methods for optimization, because mathematics offer almost inexhaustible
tricks that can be applied to geometric space.  At least that's the hope.
 That's why I (and Ben, it seems) are interested in conceptual geometry....



-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657
Powered by Listbox: http://www.listbox.com

Reply via email to