Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!sdd.hp.com!hplabs!hpcc05!hpwrce!kingsley
From: kingsley@hpwrce.HP.COM (Kingsley Morse)
Newsgroups: comp.ai.neural-nets
Subject: Re: Scaled Conjugate Gradient (SCG). Preprint soon available.
Message-ID: <3430022@hpwrce.HP.COM>
Date: 18 Nov 90 08:26:36 GMT
References: <1990Nov17.130731.12392@daimi.aau.dk>
Organization: HP Western Response Center
Lines: 5

Sounds like the scaled approach may hold promise. How much more cpu does it need
as the number of training patterns increases? As the number of inputs 
increases? Does the cpu time increase exponentially? Polynomially? Linearly?

							Kingsley