I wrote, pertaining to problems of positive feedback causing erroneous or
uncontrollable dynamics:

> The fact that similar problems occur in Novamente inference as well as in
> the brain, suggests that they're "general system-theoretic
> problems" in some
> sense, perhaps occurring in any distributed network-oriented computing
> system.

Of course, the last phrase is an overstatement.  We know some distributed
network-based computing systems that don't experience such problems, but
these systems are sorely limited in capability.

A future science could include a general characterization of "positive
feedback related learning problems", and a characterization of those
network-based computing systems that will experience them.  It might then
turn out that some of the elements of this characterization, overlapped with
an independently defined characterization of those network-based computing
systems capable of advanced intelligence.

This is the kind of theory that would be part of a real "science of complex
systems" (a thing that doesn't really exist yet -- I think "complexity
science" today consists of some nice general principles together with a
grab-bag of system-specific scientific theories and observations related to
the general principles.  Theories with both general scope and detailed
implications are pretty much lacking.)

-- Ben G

-------
To unsubscribe, change your address, or temporarily deactivate your subscription, 
please go to http://v2.listbox.com/member/[EMAIL PROTECTED]

Reply via email to