Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!tut.cis.ohio-state.edu!ucbvax!dog.ee.lbl.gov!nosc!watop!frost From: frost@watop.nosc.mil (Richard Frost) Newsgroups: comp.ai.neural-nets Subject: Re: Are Conjugate Gradient algorithms any good? + large training sets Message-ID: Date: 24 Mar 91 08:06:25 GMT References: <1991Mar4.142559.21857@daimi.aau.dk> <^9B&5R#@warwick.ac.uk> <91Mar7.145659edt.437@neuron.ai.toronto.edu> <9682@exodus.Eng.Sun.COM> <10184@exodus.Eng.Sun.COM> Sender: news@nosc.NOSC.MIL Lines: 7 A collegue reported spending over 3000 Cray YMP hours training a net for genotyping on a 1.2GB data set last year. Talk about overhead problems! -- Richard Frost Naval Ocean Systems Center frost@watop.nosc.mil voice: 619-553-6960 (Note: please e-mail directly as mail header is unreliable)