On Thu, May 21, 2015 at 4:54 AM, Piaget Modeler <[email protected]>
wrote:

> YKY,
>
> I like the direction this is going. Is Genifer 3.0 implemented yet?
>
> A couple of thoughts:
>
> 1. Another way to eliminate variables is to employ analogy (i.e.,
> substitution).
>     Hofstadter's group has been exploring analogy for years.
>


​His seems to be an alternative logic...  ​and seems to require
substitutions...



> 2. What is the purpose of the registers?
>


​Say, if the registers can store variables like X, Y, then we can eliminate
the use of explicit variables.​


3. Another way to constrain search is to employ activation, (i.e., only
> search active entries in the knowledge base).
>     That is the principle behind the Neural Propositions in PAM.P2.
>


​That may be a good idea for parallel processing... perhaps even GPU?​ :)



> 4. Now that you've eliminated variables you can begin to do some
> incredible reasoning via analogy, deduction, and
>     induction:  generalization, specialization, abstraction, concretion,
> similization, dissimilization, etc. Read Michalski's
>     Inferential Theory of Learning.
>


​Thanks, I remember reading Michalski's stuff some time ago.  Yes, he's in
the same paradigm... :) ​



-------------------------------------------
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