Re: [agi] Primal Sketching

[Vladimir Nesov]

On Feb 18, 2008 1:37 AM, Bob Mottram [EMAIL PROTECTED] wrote:
 In a closed loop system what you have is a
 synchronisation between data streams.  In part the brain is trying to
 find the best model that it can and superimpose that onto the
 available data (hence the perception of lines which don't really
 exist), and in part the low level data helps to create and maintain
 the higher level models.


I think this is a very important perspective on what mind does. It
supports multiple *processes* that interact with each other,
communicating available data to tune each other, some of these
processes driven by perception, some of them driving action. Inference
is simply a process that is initiated by communicating 'premises' to
it and that is then able to communicate 'conclusion'. Processes are
learned to be in good correspondence with statistics of their I/O, so
when some data is missing they can fill it in (in retrospect,
'predict'). These processes are a simple resource that can be plugged
in to improve prediction (pattern-completion) performed by the rest of
the system.

-- 
Vladimir Nesov
[EMAIL PROTECTED]

---
agi
Archives: http://www.listbox.com/member/archive/303/=now
RSS Feed: http://www.listbox.com/member/archive/rss/303/
Modify Your Subscription: 
http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b
Powered by Listbox: http://www.listbox.com

Re: [agi] Primal Sketching

[Bob Mottram]

On 17/02/2008, Mike Tintner [EMAIL PROTECTED] wrote:
 Hope I'm not covering old ground, but I'm wondering whether any one is
 interested and would like to comment on Marr's idea of vision involving a
 primal sketch at a basic level. I'm interested, despite much ignorance here,
 because it links to the image schemas of Lakoff and co..


As far as I know nobody has ever succeeded in implementing Marr's
theory.  When you begin to start implementing it you soon realize that
the nice edge based primal sketches, such as the ones which appear in
that paper, are unrepresentative of the general case.  In many cases
the edge features do not exist, or they exist only in your mind and
not in the original pixel data.

My main criticism of many such vision theories is that they simply
fail to close the loop.  Typically they assume that vision is a bottom
up process, i.e. that things exist objectively within the data which
the system is simply measuring and passing up to higher cognitive
levels.  Unfortunately this is rarely the case, and perception is as
much of a creative process as it is one of passively recording
information.  In a closed loop system what you have is a
synchronisation between data streams.  In part the brain is trying to
find the best model that it can and superimpose that onto the
available data (hence the perception of lines which don't really
exist), and in part the low level data helps to create and maintain
the higher level models.

The brain creates multiple competing interpretations of the data, and
yet at any point in time only one of these makes it into the arena of
consciousness.  Hence in surrealist double images your mind will
sometimes flip between possible interpretations.  I remember there
were some demonstrations in Christof Koch lectures which show this
nicely.  In one you see what appears to be a rotating sphere made from
dots, and your brain will sometimes filp between interpreting that the
pattern is rotating in one direction or the opposite direction.

---
agi
Archives: http://www.listbox.com/member/archive/303/=now
RSS Feed: http://www.listbox.com/member/archive/rss/303/
Modify Your Subscription: 
http://www.listbox.com/member/?member_id=8660244id_secret=95818715-a78a9b
Powered by Listbox: http://www.listbox.com