Path: utzoo!attcan!utgpu!jarvis.csri.toronto.edu!clyde.concordia.ca!uunet!cs.utexas.edu!asuvax!ncar!unmvax!deimos!ux1.cso.uiuc.edu!ux1.cso.uiuc.edu!uxe.cso.uiuc.edu!kbesrl
From: kbesrl@uxe.cso.uiuc.edu
Newsgroups: comp.ai.neural-nets
Subject: back-prop NNs and `SAS' regression!
Message-ID: <220700005@uxe.cso.uiuc.edu>
Date: 18 Dec 89 05:29:00 GMT
Lines: 38
Nf-ID: #N:uxe.cso.uiuc.edu:220700005:000:1634
Nf-From: uxe.cso.uiuc.edu!kbesrl    Dec 17 23:29:00 1989



I have been experimenting with back-prop neural nets for the past
few months. I find that they are only as good as polynomial
regression. Actually, I ran a back-prop neural net on some
continuous mapping problems and found that they achieved the
same performance as the `SAS' statistical package.

I am wondering whether this is true of other neural models.
If so, how can one defend the use of neural nets as opposed to
statistical regression. If someone can give me pointers to any
papers that discuss these aspects, it would be appreciated.
I also request NN-experts to e-mail their comments.

I have these additional questions regarding the use of back-prop
NNs. (I have to mention here that I have been using small 3-layer
networks (5 nodes X {1 to 20 nodes} X 5 nodes) for learning continuous
mappings.)

    1. Is there a substantial benefit from using partial connections
       as opposed to fully-connected NNs? If so, in what situations
       is it advisable?
    2. I found through experimentation that the number of hidden layers
       did not matter much; it is the total number of hidden nodes
       that mattered.
    3. Is there a rule-of-thumb that sets a limit on the number of
       hidden nodes based on the number of examples/inputs/outputs?
       I find that for the best predictive accuracy (on unseen examples),
       the number of connections is approximately equal to the number
       of examples. Is this in general true?

I'd appreciate any responses at

sudha@kbesrl.me.uiuc.edu
sudhakar y. reddy
mechanical and industrial engineering
university of illinois at urbana-champaign
urbana, il 61801