Machine Learning List Vol. 1 No. 08

eZine lover (@eZine)

Published in 

Machine Learning List

 · 11 months ago

 
		 Machine Learning List: Vol. 1 No. 8 
			 Sunday,  Sept 23, 1989 

Contents: 
	Symposium: Computational approaches to Concept Formation 
	Notes: How often is ML-LIST mailed out	 
	 
	 

		 
The Machine Learning List is moderated.  Contributions should be relevant to 
the scientific study of machine learning. Mail contributions to ml@ics.uci.edu. 
Mail requests to be added or deleted to ml-request@ics.uci.edu.  Back issues 
of Volume 1 may be FTP'd from /usr2/spool/ftp/pub/ml-list/V1/<N>  where N 
is the number of the issue; Host ics.uci.edu; Userid & password: anonymous 

 
---------------------------------------------------------------------- 
Date: Thu, 14 Sep 89 07:44:28 CDT 
From: "Douglas H. Fisher" <dfisher@vuse.vanderbilt.EDU> 
Subject: symposium 

 
                     CALL FOR PARTICIPATION 

                    SYMPOSIUM ON COMPUTATIONAL 
                  APPROACHES TO CONCEPT FORMATION 

                      Palo Alto, California 
                       January 6--7, 1990 

Concept formation -- the unsupervised, incremental acquisition of 
conceptual knowledge -- stands as a major open issue in cognitive 
science and artificial intelligence. However, recent progress has 
led to deeper understanding of the phenomena involved in human 
concept learning and of the possible mechanisms underlying these 
aspects of intelligent behavior.  

On January 6 and 7, 1990, a symposium on this topic will take place  
in Palo Alto, California. The meeting will bring together active  
researchers in this important area, letting them report their recent 
results and discuss unresolved problems. It will also establish  
communication among researchers from different paradigms, paving the  
way for unified theories of concept formation that cross existing  
methodological boundaries.  

Presentations will be through invitation, but to ensure participation by 
researchers without `contacts' and from a broad range of related fields,  
a number of additional non-presenting attendees will be invited. The  
ideal participant will have developed and tested (by implementation or  
experimentation) a computational theory of some aspect of concept  
formation, including: 

 - Concept formation and perception  

 - Concept formation in problem solving  

 - Concept formation and motor control 

 - Organization and indexing in concept formation 

 - Concept formation over structured objects 

 - Representation change in concept formation 

Applicants should send a short research summary (maximum of two pages) 
describing their research efforts and interests in concept formation by  
October 20, 1989, to the program chair:  

      Doug Fisher 
      Department of Computer Science 
      Vanderbilt University 
      Nashville, TN 37235, USA 
      Electronic mail: DFISHER@VUSE.VANDERBILT.EDU 
      Telephone: (615) 343--4111 

Travel support for participants may be available. For further information  
contact either Doug Fisher (at the above address), 

      Pat Langley, AI Research Branch, Mail Stop 244-17, NASA Ames Research 
        Center, Moffett Field, CA 94035, USA (LANGLEY@PTOLEMY.ARC.NASA.GOV), or 

      Michael Pazzani, Department of Information and Computer Science,   
        University of California, Irvine, CA 92717 (PAZZANI@ICS.UCI.EDU) 

This symposium is the second in an annual series of meetings organized  
by the Institute for the Study of Learning and Expertise, a nonprofit  
organization devoted to encouraging research and education in machine 
learning and related disciplines. The results of the 1989 symposium, which 
focused on scientific discovery and theory formation, is scheduled to appear  
as a collected volume early in 1990.  
---------------------------------------------------------------------- 
From: ml-request@ics.uci.edu 
Subject:   How often is ML-LIST mailed out	 

Some people, obviously empirical learners, were under the impression 
that ML-LIST would be mailed out weekly.  There's obviously a danger 
in generalizing from a small sample set.  When ML-LIST is mailed out 
is a function of the number of messages received, the date since the  
last mailing, and how busy the moderator is.  And since we are on the 
topic of the amount of messages received, several people have propose 
reviews of IJCAI talks....  -MP 
---------------------------------------------------------------------- 

END of ML-LIST 1.8