Xref: utzoo comp.ai:4625 comp.ai.neural-nets:841
Path: utzoo!attcan!utgpu!jarvis.csri.toronto.edu!rutgers!tut.cis.ohio-state.edu!purdue!ames!uhccux!lee
From: lee@uhccux.uhcc.hawaii.edu (Greg Lee)
Newsgroups: comp.ai,comp.ai.neural-nets
Subject: Re: Connectionism, a paradigm shift?
Message-ID: <4559@uhccux.uhcc.hawaii.edu>
Date: 13 Aug 89 20:18:55 GMT
References: <9143@thorin.cs.unc.edu>
Organization: University of Hawaii
Lines: 13

From article <9143@thorin.cs.unc.edu>, by coggins@coggins.cs.unc.edu (Dr. James Coggins):

>5. Neural nets raise lots of engineering questions but little science.

Judging from popular accounts, and as an outsider to the field, this is
the impression I get -- that NNs are an attempt to do technology without
science.  I have seen what I take to be kindred approaches in my own
field, linguistics.  The idea seems to be that one can escape the
necessity to achieve an understanding of human perception and leave that
to a machine (or algorithm, rather).  Since scientific understanding
(new and old) is so difficult to come by, it's a very seductive idea.
But not a reasonable one.
				Greg, lee@uhccux.uhcc.hawaii.edu