Draw me an invariant representation of any object in the world - per your or 
any other method.

And if you want to get your knickers into a terrible twist,  draw me an 
invariant representation of

"line"    (a line - the graphical entity)

or your fave:

"dot"  (the graphical entity).




From: Sergio Pissanetzky 
Sent: Friday, July 20, 2012 9:23 PM
To: AGI 
Subject: RE: [agi] Re: How the Brain Works -- new H+ magazine article, by me


Mike,

 

You are fast!

 

Well, yes, I do, it is emergent inference. You start from a mathematical 
representation of knowledge known as a causal set, which is the same as as 
finite algorithm, and it maps directly via the inference to a hierarchy that is 
invariant and represents the same knowledge. 

 

There is no question about that. There is no question either about the physical 
reality of these hierarchies. Physics says that symmetries result in 
structures. The causal set has symmetries, and the structures follow as a 
result. That simple. 

 

The question would be to explain how something so physical, so real, that we 
observe all the time, overlaps with concepts. Or to put it diferently, what if 
anything is different between a concept and a mathematical/physical hierarchy. 
And, if there is a difference, whether that difference is essential or just 
circumstancial, perhaps something that philosophers had to assume in order to 
continue their thinking and may be now willing to change in view of the 
evidence. 

 

Sergio

 

 

From: Mike Tintner [mailto:[email protected]] 
Sent: Friday, July 20, 2012 3:00 PM
To: AGI
Subject: Re: [agi] Re: How the Brain Works -- new H+ magazine article, by me

 

Sergio: I noticed that Jeff Hawkins in On Intelligence writes about "invariant 
representations," which are hierarchies, but never explains how they come into 
existence. I am just a little confused.

 

I wonder whether you have an outstanding point there. Everyone *talks* about 
"invariant representations". Does anyone anywhere have any AI-worthy 
explanation of their nature/origin whatsoever?

 

(Of course, invariant representations overlap with concepts. There are 
psych/phil. explanatory theories of concepts, but that's why I put in 
"AI-worthy". I suspect they are all v. vague).

      AGI | Archives | Modify Your Subscription
     
     

 

      AGI | Archives  | Modify Your Subscription   



-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-c97d2393
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-2484a968
Powered by Listbox: http://www.listbox.com

Reply via email to