home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.ai.neural-nets
- Path: sparky!uunet!cs.utexas.edu!sdd.hp.com!saimiri.primate.wisc.edu!ames!kronos.arc.nasa.gov!butch!netcomsv!netcom.com!gperkins
- From: gperkins@netcom.com (Glen C. Perkins)
- Subject: Re: Need help on Neural-network learning
- Message-ID: <1993Jan22.181211.6471@netcom.com>
- Organization: Netcom - Online Communication Services (408 241-9760 guest)
- References: <qq6qXB7w164w@cellar.org>
- Date: Fri, 22 Jan 1993 18:12:11 GMT
- Lines: 36
-
- tsa@cellar.org (The Silent Assassin) writes:
-
- >I only recently got interested in neural networks. I believe I understand
- >how they work, but I have some questions:
-
- >How many hidden layers do most neural networks have? Does the typical NN
- >have an input layer, a hidden layer, and an output layer, or several hidden
- >layers?
-
- There are a vast number of different architectures, but networks
- having one or two hidden layers seem to be the norm.
-
- >How do NN's learn? Other than randomly changing weights, how do they
- >"back-propagate" or whatever?
-
- There are too many network architectures to answer this briefly. A
- good explanation can be found in "Parallel Distributed Processing"
- by Rummelhart and MacClellan (sp?) and several other introductory
- books. You need the diagrams in the books to follow the explanations.
-
- >I finally discovered, at the age of 21, what all of my friends had found out
- >at 12 or 13-that your parents are just as fucked-up and wierd as everyone
- >else. Politically Correct: Socially, Politcally, and Environmentally
- >concious to the point of nausea. tsa%cellar@tredysvr.tredydev.unisys.com
-
- I found out at age 30 just how wonderful my parents were. Please
- restrict your gratuitous social and political commentary to the
- appropriate newsgroups.
- --
- +-----------------------+---------------------------------------------------+
- |--- Glen C. Perkins ---| |
- | <gperkins@netcom.com> | "Don't forget, your mind |
- | Native Guide Software | only *simulates* logic." |
- | Palo Alto, California | |
- +-----------------------+---------------------------------------------------+
-
-