[lbo-talk] What's at stake?/AI again

[andie nachgeborenen]

Look, just because what I say can be translated into
Chinese doesn't mean I speak in Chinese. I was
thinking about mental processes that might operate in
connectionist nets, or by mental models on the
Johnson-Laird picture, or schemas, etc. These
processes can be represented as the output of a Turing
machine. That doesn'r mean that's more than a
translation. 

--- John Thornton <jthorn65 at mchsi.com> wrote:
> 
> >Btw, all
> >thinking, algorithmic or not, _can_ be represented
> as
> >the output of a Turing machine, but it turns out
> that
> >this is not a useful or illuminating fact beyond
> the
> >most abstract level of analysis. jks
> 
> I don't think so. The definition of what is or isn't
> computational (i.e. 
> algorithmic) is whether it can or can not be done
> with a Turing machine. 
> The Church-Turing Thesis is that Turing machines are
> formal versions of 
> algorithms. No computational procedure is an
> algorithm unless it can be 
> presented as a Turing machine. Church's work shows
> that any computable 
> (i.e. algorithmic) function can be transformed into
> an expression in the 
> lambda-calculus. Church's work is equivalent to
> Turing's description of a 
> LCM. What non-algorithmic function did you have in
> mind?
> 
> John Thornton
> 
> 
> ___________________________________
>
http://mailman.lbo-talk.org/mailman/listinfo/lbo-talk

__________________________________
Do you Yahoo!?
Free Pop-Up Blocker - Get it now
http://companion.yahoo.com/