From newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.ecf!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!qt.cs.utexas.edu!cs.utexas.edu!uunet!tdatirv!sarima Mon Dec 16 11:01:18 EST 1991
Article 2057 of comp.ai.philosophy:
Path: newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.ecf!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!qt.cs.utexas.edu!cs.utexas.edu!uunet!tdatirv!sarima
>From: sarima@tdatirv.UUCP (Stanley Friesen)
Newsgroups: comp.ai.philosophy
Subject: Re: Neuron based neural nets
Message-ID: <308@tdatirv.UUCP>
Date: 11 Dec 91 22:50:46 GMT
References: <3942@papaya.bbn.com> <58114@netnews.upenn.edu> <3949@papaya.bbn.com> <58348@netnews.upenn.edu> <3962@coconut.bbn.com>
Reply-To: sarima@tdatirv.UUCP (Stanley Friesen)
Organization: Teradata Corp., Irvine
Lines: 27

In article <3962@coconut.bbn.com> cbarber@bbn.com (Chris Barber) writes:
|Because electric impulses travel outward from the body of the neuron out
|to the end of the axon, not the other way around.  Backpropagation requires
|that somehow a signal travels from neurons in deeper layers back (through
|the axon) to earlier neurons.  If this happens at all, it must be through
|some type of chemical signal.

Or a second neuron that has an axon going the other direction.

Just because this recurrent neuron would not itself partake of backpropagation
learning is no reason to deny the possibility.

|>So they model feedback via climbing fibers, not chemistry.  Whether
|>this counts as backpropagation per se, I don't know.
|
|This isn't backpropagation at all. What they seem to be talking about here is
|a kind of feedback loop.  The climbing fibers project back to the neurons that
|are supposed to learn and thus can influence them without resorting to
|backpropagation "magic".

I had always assumed that backpropagation was just a computaionally simplified
version of this sort of feedback.  What is there about backpropagation that
is different than recurrent axons or neurons?
-- 
---------------
uunet!tdatirv!sarima				(Stanley Friesen)



