home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.ai.neural-nets
- Path: sparky!uunet!sun-barr!ames!elroy.jpl.nasa.gov!sdd.hp.com!ux1.cso.uiuc.edu!m.cs.uiuc.edu!vela!wsu-cs!wsu-eng.eng.wayne.edu!uds
- From: uds@wsu-eng.eng.wayne.edu (Seetamraju Udaybhaskar)
- Subject: Re: Questions on the RCE method
- Message-ID: <1992Aug18.212531.14751@cs.wayne.edu>
- Keywords: rce method, scofield (1988)
- Sender: usenet@cs.wayne.edu (Usenet News)
- Reply-To: uds@wsu-eng.eng.wayne.edu (Seetamraju Udaybhaskar)
- Organization: Wayne State University, Detroit
- References: <66306@hydra.gatech.EDU>
- Date: Tue, 18 Aug 1992 21:25:31 GMT
- Lines: 21
-
- In article <66306@hydra.gatech.EDU> gt3451a@prism.gatech.EDU (PETERSON,RICHARD JOHN) writes:
- >I am trying to implement the RCE method described by Scofield
- >
- >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
-
- I heard that they just announced their method in the
- literature, but have kept their technique a secret (after
- having patented it). I also heard that they had gone
- commercial with it
-
- So my guess is that you wont knwo anything about it. Even if
- you do, beware of patent-infringement suits...
-
-
- Seetamraju Udaya Bhaskar Sarma
- (email : seetam @ ece7 . eng . wayne . edu)
-
- Or am I confusing this RCE net with something similar ?
-