Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!nntp.club.cc.cmu.edu!godot.cc.duq.edu!ddsw1!panix!bloom-beacon.mit.edu!spool.mu.edu!howland.reston.ans.net!math.ohio-state.edu!caen!night.primate.wisc.edu!hpg30a.csc.cuhk.hk!hkuxb.hku.hk!hkuxa.hku.hk!h9218252
From: h9218252@hkuxa.hku.hk (IP Yu Ting)
Subject: ALOPEX for filtering EPs ?
Message-ID: <D1nJw3.9rw@hkuxb.hku.hk>
Sender: usenet@hkuxb.hku.hk (USENET News System)
Nntp-Posting-Host: hkuxa.hku.hk
Organization: The University of Hong Kong
X-Newsreader: TIN [version 1.1 PL6]
Date: Sat, 31 Dec 1994 01:52:51 GMT
Lines: 16


I'm using an NN to filter visual and auditory EPs.  I have an earlier
version using BP as the training algorithm.  Now I try to implement
the ALOPEX training method.

I know that Alopex has advantages over BP in that it can use any error
measure and transfer functions, uses only local information, can be
used in feedback networks and its stochastic nature, etc.

But I'm wondering how well may this method suit to signal processing
problems.  I would like to hear more opionions or comments on that.

Thank you very much.

--Deryck

