Xref: utzoo comp.ai.neural-nets:316 comp.ai:2594
Path: utzoo!attcan!uunet!husc6!bloom-beacon!tut.cis.ohio-state.edu!mailrus!uflorida!novavax!proxftl!tomh
From: tomh@proxftl.UUCP (Tom Holroyd)
Newsgroups: comp.ai.neural-nets,comp.ai
Subject: Re: Learning arbitrary transfer functions
Summary: Connectionist Models Summer School
Message-ID: <1031@proxftl.UUCP>
Date: 15 Nov 88 20:59:46 GMT
References: <399@uvaee.ee.virginia.EDU> <32183@bbn.COM>
Reply-To: tomh@proxftl.UUCP (Tom Holroyd)
Organization: Proximity Technology, Ft. Lauderdale
Lines: 16

Another paper is "Learning with Localized Receptive Fields," by John Moody
and Christian Darken, Yale Computer Science, PO Box 2158, New Haven, CT 06520,
available in the Proceedings of the 1988 Connectionist Models Summer School,
published by Morgan Kaufmann.

They use a population of self-organizing local receptive fields, that cover
the input domain, where each receptive field learns the output value for the
region of the input space covered by that field.  K-means clustering is used
to find the receptive field centers.  Interpolation via weighted average of
nearby fields.  1000 times faster convergence than back-prop with conjugate
gradient.

Tom Holroyd
UUCP: {uflorida,uunet}!novavax!proxftl!tomh

The white knight is talking backwards.