IUBio

Whence cybernetics?

Garry Holmen garry at mdavcr.mda.ca
Wed Jul 7 17:55:28 EST 1993


>>|> 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



More information about the Neur-sci mailing list

Send comments to us at biosci-help [At] net.bio.net