Re: Is the Curt net a kind of decision tree?


"Curt Welch" <curt@xxxxxxxx> wrote in message
news:20060629173750.653$8l@xxxxxxxxxxxxxxxxx
...
The whole point to me would be, that it appears that all those terms like
"decision tree", "classiciations", "a stream of symbols" etc..are in the
eye of the human beholder here, especially of Curt. In the same way, one
can "see" (with enough metaphysical fantasy) all kinds of things for
instance in a chemical process observed under a microscope. Maybe
somewhere in the spaces between nuclei and electron clouds of atoms there
are green little men doing walki-talki with each other and "process
information" before they marry or divorce each other.

Of course. This is how we use language to gain all our understanding of
the universe. Gravity is in the eye of the beholder.

I doubt it.

Everything is in the eye of the beholder.

All we experience and know yes - but that is not everything.


The point of playing with all these terms is an
attempt to find the best possible language for describing events we see in
nature.

No need: the natural sciences developed succesfully their appropriate
languages to describe and predict. Information-AI Voodoo is just noise in
that channel.

A good test for the quality of any language is its ability to give
us predictive powers over the future. If you want to build a machine, you
must have some power to predict what it will do in the future, before you
build it.

All engineers will agree.

All this playing with terms like decision tree and
classifications and symbols and information are just attempts to find a
workable language for describing and predicting the behavior the machines
we are trying to build. We are just searching for the abstraction that
will best help us solve the problem of building intelligent machines.

The problem is not building machines, but how to define and measure machine
intelligence. It appears that everybody can concoct his/her own definition
of machine intelligence still. This is not a sign of a mature science. And
given the fact that already for some decades this definitional discussion
takes place with only more diverse and controversial ideas on it emerging I
would not put my money on it.


.

Relevant Pages

  • Re: New Cobol compiler written in Cobol
    ... machines at the time were the IBM 7090 and similar 7040. ... the 14xx line had grown to become the dominant business computer. ... Programmers won't put up with cryptic languages like C++ ... They'll use a language they can understand at a glance. ...
    (comp.lang.cobol)
  • Re: What does the future of computing hold?
    ... sophisticated views about boiling language down or not. ... deterministic physical machines, or do you follow Turing and think, ... We may have metaphysical souls, but the fact that computers are lousy at ... For ethical reasons, you cannot grow human babies to ...
    (comp.programming)
  • Re: What does the future of computing hold?
    ... sophisticated views about boiling language down or not. ... deterministic physical machines, or do you follow Turing and think, ... We may have metaphysical souls, but the fact that computers are lousy at ... humans are. ...
    (comp.programming)
  • Re: what is etymology? (linguistics and biology)
    ... the latter to Old English haleg and holeg, ... The profane language!LOG belongs to the earthly realm ... OC was the eye in general, ... The inverse of log is GOL, ...
    (sci.lang)
  • Re: PEP 3131: Supporting Non-ASCII Identifiers
    ... But you can't reliably verify by eye. ... Portuguese at least well enough to get by, ... even know what language it is in. ...
    (comp.lang.python)