NetNews Usenet Archive 1992 #16/NN_1992_16.iso/spool/comp/ai/neuraln/2863

Internet Message Format | 1992-07-21 | 1.8 KB

Path: sparky!uunet!caen!hellgate.utah.edu!cc.usu.edu!sl859
From: [e-mail]
Newsgroups: comp.ai.neural-nets
Subject: Thanks Neural Nets, and Brains?
Message-ID: <[e-mail]>
Date: 21 Jul 92 16:20:33 MDT
Organization: Utah State University
Lines: 27

Hey Neural Netters,

    I posted a message a while back and wanted to thank everyone
for their replies.  They were very helpful, although we have a long
way from being done, but we have a good idea where to go with much
of the suggestions given as replies.  I also have a better understanding
of the fact that you should not understand much of the Backpropagation
workings, and am becoming very familiar with data tweaking and data
conflaggellation, but that's one of the joys of Neural Nets :).
     I do have an additional question.  How extensive has the research
been on neurons of a neural net and the actual neurons of the brain?  I
am interested mostly out of curiosity, but from what I've read I can only
deduct that we still haven't got a very good model of the actual workings
of the brain neurons, let alone how to model them with computers.  I can
imagine a reason would be that people who get involved in computers AI
don't have the biological experience (or patience to get both degrees!)
to know the inner most workings of these cells and viceversa.  One book
I read however claimed even the best NN's simulated by computers barely
reach the intellectual capacity of a tapeworm!  (I liked that quote!)
    Well, thanks to all those who responded some time ago and thanks
for reading this other question.  I find much of this material very
fascinating, and apreciate the pointers posted for the beginners as well.
                Keep trainin' and testin' all those Neurons!
                    wReam...
                    (Raymond Bingham)
                Internet:[e-mail]