Path: utzoo!utgpu!news-server.csri.toronto.edu!rutgers!cs.utexas.edu!uwm.edu!rpi!zaphod.mps.ohio-state.edu!samsung!munnari.oz.au!murtoa.cs.mu.oz.au!rgg
From: rgg@cs.mu.oz.au (Rupert G. Goldie)
Newsgroups: comp.ai.neural-nets
Subject: Implementation question
Keywords: implementation
Message-ID: <3091@murtoa.cs.mu.oz.au>
Date: 18 Jul 90 04:46:03 GMT
Organization: Comp Sci, Melbourne Uni, Australia
Lines: 13

Profiling a backpropagation or quickprop net shows a large cost in computing
the activation function (I was using a sigmoid). What methods are people 
using to reduce this cost ? Approximating the function with a polynomial, or
rolling your own exponent function seem like possibilities, but does this
increase the learning time or have other side-effects ?
Thanks, 

	Rupert.
----
Rupert G. Goldie				rgg@munmurra.cs.mu.OZ.AU
Computer Science Honours Student, University of Melbourne

"Nobody expects the Spanish Inquisition"