Path: utzoo!attcan!uunet!samsung!zaphod.mps.ohio-state.edu!wuarchive!wuche2!joshi
From: joshi@wuche2.wustl.edu (Amol Joshi)
Newsgroups: comp.ai.neural-nets
Subject: Re: back-prop NNs and `SAS' regression!
Message-ID: <1989Dec18.210859.23621@wuche2.wustl.edu>
Date: 18 Dec 89 21:08:59 GMT
References: <220700005@uxe.cso.uiuc.edu>
Reply-To: joshi@wuche2.UUCP (Amol Joshi)
Organization: Washington University in St. Louis
Lines: 40

In article <220700005@uxe.cso.uiuc.edu> kbesrl@uxe.cso.uiuc.edu writes:
>
>
>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.
>
	the techniques of multi-variable analysis are not suited to non-linear
	phenomena and many real problems are non-linear.
	even though non-linear regressions can treat non-linear phenomena, they
	require that the structure of the math model be prefixed.
	it is in these cases that backprop nets would be more useful.

>    1. Is there a substantial benefit from using partial connections
>       as opposed to fully-connected NNs? If so, in what situations
>       is it advisable?
	
	with fully connected NNs, it is difficult to decipher the dominant
	relationships among input and output variables. with lesser number of
	connections, it would be possible to extract some "rules" with more
	ease when it is necessary. 
	the problem with using lesser number of connections is that it  becomes
	more difficult (typically) to obtain convergence. this is especially true
	if the number of nodes that one is using is very near the "minimum" needed
	to represent the function in question. e.g. i found it very difficult to get
	convergence for representing XOR function with  just four nodes (in three
	layers - i.e. to get textbook solution). it was easier to get convergence
    for a 5-node network.

	in the last AI Expert, there is an article about NNs and statistics. 

:amol

-- 

------------------------------------------------------

amol joshi			dept of chemical engrg