home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.ai.neural-nets
- Path: sparky!uunet!stanford.edu!leland.Stanford.EDU!leland.Stanford.EDU!ledwards
- From: ledwards@leland.Stanford.EDU (Laurence James Edwards)
- Subject: Re: Neural Nets and Brains
- Message-ID: <1992Jul25.210157.6853@leland.Stanford.EDU>
- Sender: news@leland.Stanford.EDU (Mr News)
- Organization: DSG, Stanford University, CA 94305, USA
- References: <arms.711986585@spedden> <1992Jul24.164544.11876@cs.ucf.edu>
- Date: Sat, 25 Jul 92 21:01:57 GMT
- Lines: 26
-
- In article <1992Jul24.164544.11876@cs.ucf.edu>, clarke@acme.ucf.edu (Thomas Clarke) writes:
- |> In article <arms.711986585@spedden> arms@cs.UAlberta.CA (Bill Armstrong)
- |> writes:
- |> > .... My point
- |> > was that BP nets use continuous signals and the brain doesn't -- an
- |> > obvious very significant difference. I was asking why people would
- |> > expect to understand the brain by studying a system (BP) that is
- |> > *different* at the most basic level of signalling.
- |> >
- |> > Don't you agree that if the brain works on 0-1 signals, then to study
- |> > the brain one could beneficially look at logical systems?
- |>
- |> I believe the brain may well use continuous or analog signals.
- |>
- |> While individual neuron action potentials are on or off, they
- |> often occcur in trains of varying frequency. The time-density of
- |> action potentials then forms an analog or continuous variable
- |> that may be processed in much the same way as a BP network.
-
- Yes, I always assumed this was the standard interpretation ... i.e. the
- activation level of the perceptron is analagous to the *rate* of firing of a
- neuron, not to the peak voltage of individual spikes. This seems pretty
- obvious to me.
-
- Larry Edwards
- edwards@sunrise.stanford.edu
-