Why are Neural Nets not AI?

Hi there,

I made an appointment to see one of my lecturers a few days back and said it
was going to be about AI.  When I got there, I asked him about Neural Nets
and he told me that NNs are not considered a branch of AI.
I didnt want to disagree but he did not explain why.  Could someone please
elaborate and explain why NNs are not considered a bramch of AI?

Thanks
Allan


0
Allan
7/29/2003 10:55:24 AM
comp.ai.neural-nets 5679 articles. 1 followers. tomhoo (63) is leader. Post Follow

2 Replies
191 Views

Similar Articles

[PageSpeed] 27

"Allan Bruce" <abruce@TAKEAWAYcsd.abdn.ac.uk> wrote in message
news:bg5k4f$kr5$1@news.abdn.ac.uk...
> Hi there,
>
> I made an appointment to see one of my lecturers a few days back and said
it
> was going to be about AI.  When I got there, I asked him about Neural Nets
> and he told me that NNs are not considered a branch of AI.
> I didnt want to disagree but he did not explain why.  Could someone please
> elaborate and explain why NNs are not considered a bramch of AI?
>

I think the short answer is that neural networks have branched off from the
main body of AI work (which is largely neglected now) and become a field of
research in their own right.

The primary use of NNs is no longer to simulate "intelligent" behaviour;
rather they are a generalised mathematical tool which can be used to solve
control problems for which the parameters are not well understood (or are
not analytic).

That said, there are still branches of NN research which are after the Holy
Grail of AI, but mainstream researchers tend to dissociate themselves from
these branches to protect their reputations :^).  Your lecturer may have
been doing just that.

If you're interested in NNs for AI, try searching for "spiking neural
networks".  This should lead you to the right people - mostly biologists
interested in simulating the actual behaviour of the brain.

Regards
David Turner


0
David
7/29/2003 11:49:17 AM
"E. Robert Tisdale" <E.Robert.Tisdale@jpl.nasa.gov> wrote in message news:<3F2971CC.7020501@jpl.nasa.gov>...
> Allan Bruce wrote:
> 
> > I made an appointment to see one of my lecturers a few days back
> > and said it was going to be about [Artificial Intelligence (AI)].
> > When I got there, I asked him about Neural Nets
> > and he told me that NNs are not considered a branch of AI.
> > I didn't want to disagree but he did not explain why.
> > Could someone please elaborate
> > and explain why NNs are not considered a branch of AI?
> 
> Your lecturer was expressing a personal opinion.
> I think that most subscribers to the comp.AI.neural-nets newsgroup
> consider Neural Networks to be a "branch" or, at least,
> somehow a "part" of Artificial Intelligence.
> I would say that your lecturer adheres to a *minority* opinion.
> If this is really of interest to you,
> you might wish to explore the issue further with your lecturer
> remembering, of course, to be respectful of other people's opinions
> even when they clash with your own.

You can find real AI based on artificial Neural Network here
http://www.proto-mind.com .
0
agborsen
8/2/2003 2:36:32 AM
Reply: