Re: Another take on self-learning

On Thu, Jul 31, 2008 at 06:08:22PM +0400, Eugene Crosser wrote:
> Here is one more theoretical development which may (or may not) be of 
> interest in the context of document classification:
> 
> http://www.spectrum.ieee.org/print/4982

thanks for the pointer(s). Yeah, I think it is surely of interest for doc - 
actually, generic objects - classification; pity it's a 'patented theory'.
Their shrewd biz model resembles MS' 'open' stuff: luring (open) devel to 
use some (almost) open/free stuff and build biz/value on and around [other]
_core_ nonfree, patented, stuff. And should you think of building your own
_core_ stuff, be prepared to challenge a thick patents portfolio.

Devels are advised to carefully read and weight the (not so) fine prints
before jumping on Numenta's ship. 
Better study how brain works and figure out your own way to match it; HTM
looks like a label to something around since long in the field.

Final thought: if HTM is the way (human) brain works, are we all
supposed to pay per-thought royalties to Numenta, or the converse?

That's the hard mid-summer question.



'take care' @all ;)

-- 
paolo

-------------------------------------------------------------------------
This SF.Net email is sponsored by the Moblin Your Move Developer's challenge
Build the coolest Linux based applications with Moblin SDK & win great prizes
Grand prize is a trip for two to an Open Source event anywhere in the world
http://moblin-contest.org/redirect.php?banner_id=100&url=/