Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!tut.cis.ohio-state.edu!ukma!xanth!lll-winken!ncis.llnl.gov!afit-ab!efrethei
From: efrethei@afit-ab.arpa (Erik J. Fretheim)
Newsgroups: comp.ai.neural-nets
Subject: Re: Training
Message-ID: <997@afit-ab.arpa>
Date: 22 Mar 89 04:05:31 GMT
References: <2698@sun.soe.clarkson.edu> <2351@buengc.BU.EDU> <1577@vicom.COM>
Reply-To: efrethei@blackbird.afit.af.mil (Erik J. Fretheim)
Distribution: na
Organization: Air Force Institute of Technology; WPAFB, OH
Lines: 37


In article <1577@vicom.COM> hal@vicom.COM (Hal Hardenbergh (236)) writes:
>In article <2351@buengc.BU.EDU> bph@buengc.bu.edu (Blair P. Houghton) writes:
>>In article <2698@sun.soe.clarkson.edu> spam@clutx.clarkson.edu writes:
>>>Has anyone come up with a good way to train a net
>>>without knowing a "target" in advance?
>>[...]
>>>All the learning methods I've studied so far
>>>are inadequate for this.
>>
>>Sounds like good ol' negative reinforcement to me.
>>
>>You could send it to a Zen Buddhist monastery, or an English public
>>school...
>>
>>Have you tried just getting a degree in education and coding it?
>
>
>As long as we are simulating artificial neural nets in software (if simulating

"Emulating" I belive is the correct term, if not the term of choice.


Of course, it seems rather natural that speeding up backprop is like all of
the rest of pattern recognition, an art rather than a science.  After all, if
the results were predictable would it be any fun any more?










.signature and .disclaimer to be invented someday.