Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!tut.cis.ohio-state.edu!unmvax!ncar!tank!uwvax!astroatc!johne
From: johne@astroatc.UUCP (Jonathan Eckrich)
Newsgroups: comp.ai.neural-nets
Subject: Re: Why Neural Nets?
Message-ID: <1686@astroatc.UUCP>
Date: 7 Apr 89 21:01:47 GMT
References: <458@uvaee.ee.virginia.EDU>
Organization: Astronautics Technology Cntr, Madison, WI
Lines: 34

(Ali Minai) writes:

>FOR WHAT ARE NEURAL NETWORKS USEFUL?

I know that you are looking for more specifics to this question than I am
able to supply.  I can, however, tell you how in my experience, I find NNs
useful.

When I was in school, I attended a biomedical class where we studied pattern
recognition techniques.  One of the problems that the instructor made sure
we would have exposure to was that of finding the 'right' paramters to measure.
No matter what the pattern is, with conventional methods of pattern recognition,
the prerequisite work to each specific problem is to discover and catagorize
parameters that are necessary to suitably recognize all possible patterns
in the defined pattern space.

For example, with the task of recognizing human faces, certain parameters or
characteristics of faces in general must be established.  Depending on the 
variety of faces that are to be used (age, sex, ethnic origin), this may not
be a trivial task.  With a NN approach, this data only need be presented to
the net, and it will in essence 'see' and use those parameters that lead
toward discrimination of different patterns, while ignoring the others.

Of course, the approriate net structure will have to be used.  In addition,
the 'best' activation and weight modification algorithms will need to be
developed. I don't know, but maybe this just puts the problem into a dif-
ferent form.  Someone more knoledgeable than I would have to answer that.

------
Ignore any spelling errors.  I quickly proof read this.

-- 
				   (rutgers, ames)!uwvax!astroatc!johne
					    nicmad!astroatc!johne