home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!darwin.sura.net!wupost!gumby!destroyer!ncar!noao!amethyst!organpipe.uug.arizona.edu!organpipe.uug.arizona.edu!bill
- From: bill@nsma.arizona.edu (Bill Skaggs)
- Newsgroups: comp.ai.neural-nets
- Subject: Re: Neural Nets and Brains
- Message-ID: <BILL.92Jul24111728@ca3.nsma.arizona.edu>
- Date: 24 Jul 92 18:17:28 GMT
- References: <1992Jul21.162033.57397@cc.usu.edu> <1992Jul23.013755.18847@hubcap.clemson.edu>
- <arms.711907358@spedden> <BILL.92Jul23135614@ca3.nsma.arizona.edu>
- <arms.711935064@spedden> <BILL.92Jul23224539@ca3.nsma.arizona.edu>
- <arms.711986585@spedden>
- Sender: news@organpipe.uug.arizona.edu
- Organization: ARL Division of Neural Systems, Memory and Aging, University of
- Arizona
- Lines: 25
- In-Reply-To: arms@cs.UAlberta.CA's message of 24 Jul 92 14: 03:05 GMT
-
- arms@cs.UAlberta.CA (Bill Armstrong) writes:
-
- >In sum: to study the brain, in my opinion, based on ignorance of
- >how the brain works, is that one should study a system that works
- >on logical signals. Although ALNs might help in this, they are
- >not designed as a brain model at all, and different learning
- >algorithms would have to be developed to capture the learning
- >properties of neurons.
- >
- >Are we getting closer?
-
- This seems entirely reasonable to me.
-
- I would like to stress, though, that, while there are good reasons to
- pay special attention to binary-neuron networks, there is no need to
- *avoid* looking at scalar-neuron networks. For some subsystems of the
- brain, at certain levels of analysis, scalar neurons are actually
- preferable. The oculomotor system is the best example I know of:
- when the variables of the system are taken to be firing rates and eye
- position angles, the system is very nearly linear (David Robinson is
- responsible for working this out). This very important relationship
- would probably have been completely missed had the neurons been
- treated as binary units.
-
- -- Bill
-