home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.ai.neural-nets
- Path: sparky!uunet!gatech!destroyer!ubc-cs!unixg.ubc.ca!kakwa.ucs.ualberta.ca!alberta!arms
- From: arms@cs.UAlberta.CA (Bill Armstrong)
- Subject: Re: Thanks Neural Nets, and Brains?
- Message-ID: <arms.711932483@spedden>
- Sender: news@cs.UAlberta.CA (News Administrator)
- Nntp-Posting-Host: spedden.cs.ualberta.ca
- Organization: University of Alberta, Edmonton, Canada
- References: <1992Jul21.162033.57397@cc.usu.edu> <1992Jul23.013755.18847@hubcap.clemson.edu> <arms.711907358@spedden> <50783@dime.cs.umass.edu>
- Date: Thu, 23 Jul 1992 23:01:23 GMT
- Lines: 22
-
- connolly@rabbit.cs.umass.edu (Christopher Ian Connolly) writes:
-
- >In article <arms.711907358@spedden> arms@cs.UAlberta.CA (Bill Armstrong) writes:
- >>First off, isn't it rather strange that the most widespread artificial
- >>model of neural operation. the multilayer perceptron, uses continuous
- >>quantities on its connections, while the dendrites and axons of
- >>neurons use "zero or one" type action potentials?
-
- >Don't forget that electrical synapses (gap junctions) are an analog
- >means of intercellular communication. Whether they represent a
- >significant part of brain function is another question entirely.
- >--
-
- Of course, and in adaptive logic networks (ALNs), if you want to deal with
- continuous signals, you need to have input conversions which generate
- booleans: for example thresholds x>= const.
-
- --
- ***************************************************
- Prof. William W. Armstrong, Computing Science Dept.
- University of Alberta; Edmonton, Alberta, Canada T6G 2H1
- arms@cs.ualberta.ca Tel(403)492 2374 FAX 492 1071
-