home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!haven.umd.edu!darwin.sura.net!paladin.american.edu!gatech!prism!gt3451a
- From: gt3451a@prism.gatech.EDU (PETERSON,RICHARD JOHN)
- Newsgroups: comp.ai.neural-nets
- Subject: Questions on the RCE method
- Keywords: rce method, scofield (1988)
- Message-ID: <66306@hydra.gatech.EDU>
- Date: 18 Aug 92 18:46:45 GMT
- Organization: Georgia Institute of Technology
- Lines: 26
-
-
- I am trying to implement the RCE method described by Scofield
- in his paper "Learning internal representations in the coulomb
- energy network" ICNN vol I, 271-275 (July 1988).
-
- Unfortunately he gives little details about the way he implemented
- the simple XOR exemple and I'm not even able to do that. I don't
- know how he chose the number of layers and the number of outputs
- for each layer. I don't know either how he did the learning, i.e
- the way he presented the different patterns and the class he associated
- to each pattern.
-
- If anybody can give me more details about this implementation I would
- be very glad to hear from him.
-
- Thanks a lot.
-
- Herve Marzio
-
- Please address you answers to : qscsihm@prism.gatech.edu
-
- --
- PETERSON,RICHARD JOHN
- Georgia Institute of Technology, Atlanta Georgia, 30332
- uucp: ...!{allegra,amd,hplabs,seismo,ut-ngp}!gatech!prism!gt3451a
- ARPA: gt3451a@prism.gatech.edu
-