Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!rochester!cornellcs!newsstand.cit.cornell.edu!news.acsu.buffalo.edu!dsinc!spool.mu.edu!uwm.edu!www.nntp.primenet.com!nntp.primenet.com!howland.erols.net!news.sprintlink.net!news-peer.sprintlink.net!news.sprintlink.net!news-pull.sprintlink.net!news.sprintlink.net!news-atl-21.sprintlink.net!interpath!news.interpath.net!news.interpath.net!sas!newshost.unx.sas.com!saswss
From: saswss@hotellng.unx.sas.com (Warren Sarle)
Subject: Re: Supervised/Unsupervised learning hybrid - does it exist?
Originator: saswss@hotellng.unx.sas.com
Sender: news@unx.sas.com (Noter of Newsworthy Events)
Message-ID: <E2BAFv.2Kp@unx.sas.com>
Date: Thu, 12 Dec 1996 17:40:42 GMT
X-Nntp-Posting-Host: hotellng.unx.sas.com
References: <32AF49DC.D59@nfld.com> <Pine.SOL.3.91.961212025320.3320C-100000@miles>
Organization: SAS Institute Inc.
Lines: 25


In article <Pine.SOL.3.91.961212025320.3320C-100000@miles>, Greg Heath <heath@ll.mit.edu> writes:
|> On Wed, 11 Dec 1996, Dale wrote:
|> 
|> > My friend and I are trying to do a science project related to neural nets,
|> > and we're trying to find a learning rule somewhere between supervised and 
|> > unsupervised learning. ...LARGE SNIP... So what we'd like to know is, is there
|> > a learning method whereby one gives the net a general rating of its 
|> > performance but not a desired output, and it learns how to maximize its
|> > performance. ...
|>  
|> Look up "Reinforcement Learning". The last name "Barto" and Univ. of Mass. 
|> comes to mind. Perhaps other readers can help, my references aren't within 
|> reach right now.

   Bertsekas, D. P. and Tsitsiklis, J. N. (1996), Neuro-Dynamic
   Programming, Belmont, MA: Athena Scientific, ISBN 1-886529-10-8.

-- 

Warren S. Sarle       SAS Institute Inc.   The opinions expressed here
saswss@unx.sas.com    SAS Campus Drive     are mine and not necessarily
(919) 677-8000        Cary, NC 27513, USA  those of SAS Institute.
 *** Do not send me unsolicited commercial or political email! ***

