Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!rochester!cornellcs!newsstand.cit.cornell.edu!portc01.blue.aol.com!portc02.blue.aol.com!newsfeed.pitt.edu!news.duq.edu!newsgate.duke.edu!interpath!news.interpath.net!news.interpath.net!sas!newshost.unx.sas.com!saswss
From: saswss@hotellng.unx.sas.com (Warren Sarle)
Subject: Re: [Q] Batch type learning vs. Pattern type learning
Originator: saswss@hotellng.unx.sas.com
Sender: news@unx.sas.com (Noter of Newsworthy Events)
Message-ID: <E1LrHI.MGp@unx.sas.com>
Date: Thu, 28 Nov 1996 22:51:18 GMT
X-Nntp-Posting-Host: hotellng.unx.sas.com
References:  <57bkjb$7iq@worak.kaist.ac.kr>
Organization: SAS Institute Inc.
Lines: 23


In article <57bkjb$7iq@worak.kaist.ac.kr>, sbpp@ee.kaist.ac.kr (sbpark) writes:
|> I have known that Pattern type learning is more powerful than Batch type 
|> learning. 

Sometimes, particularly for large redundant training sets, but not always.

|> But I need some papers which contain the comparison of batch and 
|> pattern type learning. Both theoretical analysis and empherical results can be 
|> a great help. 

The best theoretical analysis that I have come across is in:

   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! ***

