NetNews Usenet Archive 1992 #20/NN_1992_20.iso/spool/comp/ai/neuraln/3411

Internet Message Format | 1992-09-08 | 1.6 KB

Path: sparky!uunet!dtix!relay!afterlife!hcbarth
From: [e-mail] (Bart Bartholomew)
Newsgroups: comp.ai.neural-nets
Subject: BEP question
Message-ID: <[e-mail]>
Date: 7 Sep 92 06:42:41 GMT
Organization: The Great Beyond
Lines: 27


    I have been pondering a problem in NNs that I think should
work, but I don't know how to implement it.  While I will describe
a specific problem, the technique (if there is one) should have
a fairly wide use.
    Everyone is just born knowing that sine waves are mean zero,
variance one.  If gaussian noise is added, the variance goes up.
Some people use the variance as a measure of the signal-to-noise ratio.
    Seems like we should be able to do an epochal forward pass
in which we accumulate the output points, compute the variance,
develope an error term from the putative norm, and backpropagate that.
    One can, of course, see other such error terms.  In effect,
we have some black box in the forward pass to develop the error for
the backward pass.
    The mathematicians (I am most assuredly *not*) will probably
object if the error term is not differentiable.  My wetware feeling
(notoriously unreliable) is that if a given function is not nicely
differential, there is some reasonable transformation of it that is.
    At this point we come to the inevitable clash with the nuts-
and-bolts of the problem in deciding how to actually implement
something like this.
    Your comments please.
    Bart
--
 If there's one thing I just can't stand, it's intolerance.
*No One* is responsible for my views, I'm a committee. Please do not
infer that which I do not imply.  [e-mail]