Newsgroups: comp.ai
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!news.sprintlink.net!EU.net!ieunet!tcdcs!mmkelly
From: mmkelly@cs.tcd.ie (Mel Kelly)
Subject: Machine Learning in CBR
Message-ID: <1994Dec21.155624.6841@cs.tcd.ie>
Organization: Computer Science, Trinity College Dublin
Date: Wed, 21 Dec 1994 15:56:24 GMT
Lines: 24

 
Hello,

        I'm involved with a project that requires machine learning in
CBR.  The project is specifically involved with a forestry application.
I have access to a large database of records so any information on the
following would be greatly appreciated.

       1.  How to determine which records/cases to add to the casebase.
       2.  How to reduce approximately 100,000 records to a more
            manageable sized casebase of about 2,000 cases.

As information in this area is difficult to find, I would be grateful
for any pointers to research papers or any other useful suggestions.

Mel Kelly
AI Group,
Dept. of Computer Science,
T.C.D.,
Dublin 2,
Ireland.

return address: Mel.Kelly@tcd.ie

