Re: Whence cybernetics?

Article View: sci.cognitive

Article #761

#761

From: Garry Holmen
Date: Wed, 07 Jul 1993 22:55

16 lines
1771 bytes

>>|> Ideally, NNs should be analog machines (... that takes us quite far
>>|> back to the past). Unfortunately, the technology is not yet in place
>>|> for that. I am a true believer that it is only a matter of time,
>>|> though.
>>

NN's do not need to be analog machines. Some networks perform quite well on digital
machines. Of course if you're implementing a Net based on arithmetic propagation
as is used in backprop and many others an analog machine would be best.

I use ALNs and they're ideally suited for a digital enviroment.

What I am trying to iterate here is that just because your version of a NN would
run best on an analog machine it doesn't mean that all NNs should be analog.

Garry

Technical Details

Message-ID: <4345@map.mdavcr.mda.ca>

Path:

arc1-ca.pugleaf.net!gmd.de!Germany.EU.net!mcsun!uunet!europa.eng.gtefsd.com!howland.reston.ans.net!math.ohio-state.edu!cyber1.cyberstore.ca!vanbc.wimsey.com!mdavcr!garry

References: <ANDRZEJ.93Jul6161824@bcars182.bnr.ca> <1993Jul7.013132.11916@ee.surrey.ac.uk> <21dbfqINNkn@flop.ENGR.ORST.EDU>

Show Full Headers

Complete Article Headers

X-Google-Language: ENGLISH,ASCII-7-bit
X-Google-Thread: 10d04f,7068ba2bb8f56eb8
X-Google-Attributes: gid10d04f,public
X-Google-Thread: 10681a,94aaf0c17afb47c5
X-Google-Attributes: gid10681a,public
X-Google-Thread: 10ca9b,94aaf0c17afb47c5
X-Google-Attributes: gid10ca9b,public
X-Google-Thread: 1045ed,94aaf0c17afb47c5
X-Google-Attributes: gid1045ed,public
X-Google-ArrivalTime: 1993-07-07 19:43:27 PST
Path: arc1-ca.pugleaf.net!gmd.de!Germany.EU.net!mcsun!uunet!europa.eng.gtefsd.com!howland.reston.ans.net!math.ohio-state.edu!cyber1.cyberstore.ca!vanbc.wimsey.com!mdavcr!garry
From: garry@mdavcr.mda.ca (Garry Holmen)
Newsgroups: sci.cognitive,comp.ai.philosophy,comp.ai.neural-nets,bionet.neuroscience
Subject: Re: Whence cybernetics?
Message-ID: <4345@map.mdavcr.mda.ca>
Date: 7 Jul 93 22:55:28 GMT
References: <ANDRZEJ.93Jul6161824@bcars182.bnr.ca> <1993Jul7.013132.11916@ee.surrey.ac.uk> <21dbfqINNkn@flop.ENGR.ORST.EDU>
Followup-To: sci.cognitive
Organization: MacDonald Dettwiler, 13800 Commerce Parkway, Richmond, BC, Canada  V6V 2J3
Lines: 18

Reply to Parent Message