Re: Aaron Sloman's "The Irrelevance of Turing Machines to AI" article

From: Wolf Kirchmeir (wwolfkir_at_sympatico.ca)
Date: 08/03/04 

Date: Tue, 03 Aug 2004 09:45:25 -0400

Neil W Rickert wrote:
[...]
> My own view is that, in some sense, learning is adaptation. And I
> think computers can only adapt in ways that they have been
> preprogrammed to adapt. They cannot deal will with the unexpected.

Careful. As soon as you say a program can't do something, someone will
come along and write a program that can do it.

You claim skepticism about the relevance of statistics to the problem of
learning. Well, I can see the structure of a program that uses
statistics on its own "exsperience" to "deal with the unexpected."

Relevant Pages

  • Re: Aaron Slomans "The Irrelevance of Turing Machines to AI" article
    ... >> My own view is that, in some sense, learning is adaptation. ... >> preprogrammed to adapt. ... things that *cannot* be done by computers. ...
    (sci.cognitive)
  • Re: Is this math test too easy?
    ... >> not mathematics, nor is learning how to solve simple equations. ... Herman Rubin, Department of Statistics, Purdue University ...
    (sci.math)
  • Re: Near miss from space junk.
    ... Learning to fly IFR involves ... learning to adapt those conditioned responses to the IFR environment. ...
    (rec.aviation.piloting)
  • Re: Statistical Learning and statistics
    ... > some joint probability density Pr, then supervised learning can ... knowledge from a non-operational form to an operational form. ... definition includes much, if not all, of statistics. ...
    (sci.stat.math)
  • R versus Fortran?
    ... I have always done my statistical analyses in good old Fortran. ... I am considering learning "R" since it appears to be a very ... analysis & correlational statistics. ...
    (sci.stat.math)