From: Cliff Stabbert (cps46@earthlink.net)
Date: Sat Aug 10 2002 - 04:59:47 MDT
[I didn't get the original message or Samantha's reply in this thread]
Saturday, August 10, 2002, 6:12:29 AM, David Hart wrote:
DH> I again urge readers to ignore the emotive statements and arguments on
DH> the website and focus on the idea of a temporal-signal-based approach to
DH> software and the technical merits of the proposed implementation (COSA).
I'm finding it hard to do. I've waded through a number of pages of
handwaving "all the old paradigms suck" rhetoric and am searching for
some actual contents. Perhaps someone can point me to the actual meat
here. I don't get much from passages like this:
(http://home1.gte.net/res02khr/AI/Temporal_Intelligence.htm)
> One of the most powerful aspects of the temporal approach to intelligence
> is that it is based on a single unifying concept: the relative arrival
> times of discrete signals. Its power is in its simplicity. At the heart
> of this approach is the claim that all knowledge, regardless of type,
> consists of patterns of discrete signals, a pattern being defined as a
> set of temporal relationships. Although the number of possible patterns
> is unlimited, all patterns can be expressed in terms of only two fundamental
> relationships: signals can be either concurrent or sequential. A second
> beneficial aspect of temporal intelligence is that it is domain-independent.
> That is to say, it makes no assumptions about either the origin (sensors) or
> the destination (effectors) of signals. Finally, a temporal system is
> ideally suited to the goal of emulating what is probably the most important
> attribute of biological intelligence: the ability to learn to anticipate or
> predict the evolution of various phenomena in one's environment.
E.g. what does "all knowledge, regardless of type, consists of patterns of
discrete signals, a pattern being defined as a set of temporal
relationships" /mean/? Did I miss where he defines "knowledge"?
I don't have more than a slight clue about neural networking, so if
that's what I'm lacking to understand the above and how it
("radically!" or not) enhances/differs from established neural
networking paradigms, I'd be interested to hear.
It's not that I'm not open to a magnitude of improvement -- I'm just
more than a little sceptical, i.e., /show/ me. What's that quote from
that author about "ideas"?
-- Cliff
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:40 MDT