Copy Link
Add to Bookmark
Report
Machine Learning List Vol. 2 No. 15
Machine Learning List: Vol. 2 No. 15
Saturday, Sept 1, 1990
Contents:
Concept Clustering Implementations
Cognitive Science 1991
UCI repository of databases and domain theories
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
may be FTP'd from ics.uci.edu in /usr2/spool/ftp/pub/ml-list/V<X>/<N> or N.Z
where X and N are the volume and number of the issue; ID & password: anonymous
------------------------------
Date: Mon, 20 Aug 90 14:38:45 -0600
From: Peter Wohl <thsspxw@iitmax.iit.edu>
Subject: concept clustering implem.
I am working on implementing (incremental) symbolic conceptual clustering
on MIMD multiprocessors, so it would run "really fast".
I would be interested to get references/comments on the issue of implementation
performance of symbolic conceptual clustering methods (AutoClass, COBWEB,
CLASSIT...), like:
* performance measures and performance data (ex. how many objects-attributes-
values/second do you cluster)
* source codes available (I know about AutoClass, but I prefer C over Lisp,
believing it might be faster)
* parallel processing implementations (maybe also of supervised methods, like
IDn, if there is any around)
* application requirements (ex. how many instances would you like to cluster,
how many attributes each, real/nominal/both valued attributes... and how fast
do you expect/know to run it)
I will get back with results of this poll (and of my own work), as the interest
turns out to be.
Thanks,
-Peter
------------------------------
Date: Fri, 31 Aug 90 16:19:50 CDT
From: Kris Hammond <kris@gargoyle.uchicago.edu>
Subject: Cognitive Science 1991.
CALL FOR PARTICIPATION: COGNITIVE SCIENCE 1991
THE THIRTEENTH ANNUAL MEETING OF THE COGNITIVE SCIENCE SOCIETY
AUGUST 7TH - 10TH 1991, CHICAGO, IL
The Annual Meeting of the Cognitive Science Society is a
multi-disciplinary conference aimed at bringing together researchers
with interests related to the modeling of cognition in humans and
machines. The 1991 meeting will be held at the University of Chicago,
hosted by the Artificial Intelligence Laboratory of the Computer
Science Department.
The conference technical program will include panels, both invited and
refereed talks, and poster sessions. Videotape presentations and
computer based demonstrations are also planned. Depending on interest
and available organizers, there will also be a one day tutorial
program preceding the Meeting.
The deadline for paper and symposia submissions is March 1st, 1991.
Papers should be printed on 8.5" x 11" or A4 sized paper,
double-spaced (i.e. no more than 28 lines per page), with 1.5"
margins. Camera ready versions of papers will be required only after
authors are notified of acceptance.
Papers should be a maximum of 5000 words, (about 16 pages double
spaced), including figures, tables and diagrams.
Papers should be sent to:
Cognitive Science 1991
Department of Computer Science
University of Chicago
1100 East 58th Street
Chicago, IL 60637
All questions and requests for more detailed information concerning
the 1991 Meeting should be addressed to the program chairs:
Dr. Kristian Hammond Dr. Dedre Gentner
Department of Computer Science Department of Psychology
University of Chicago Northwestern University
1100 East 58th Street Evanston, IL 60201
Chicago, IL 60637
(312) 702-0510
Electronic Mail: cogsci91@tartarus.uchicago.edu
Fax: (312) 702-8487
------------------------------
Subject: UCI repository of databases and domain theories
Date: Wed, 15 Aug 90 10:49:27 -0700
From: "David W. Aha" <aha@ICS.UCI.EDU>
I have received several databases recently that may be of interest to the
community, including Cullen Schafer's collection of 352 case studies for
function finding today. I've included a complete but brief listing below.
Many people have recently requested databases with domain theories. Currently,
the following domain theories have been donated to this collection:
1. Nick Flann donated 6 on interpreting legal moves of chess
2. Towell, Shavlik, & Noordewier's theory for their promoter sequence data
3. J. Ross Quinlan's thyroid hormone rules for the Garavan Institute's data
4. Mike Pazzani's theory for his database on economic sanctions
Please contact me if you have any additional domain theories that you
would be willing to donate. I am also *especially* interested in
collecting databases with structured attributes and/or relations.
Simulators and data generators are also welcome.
Finally, I am now maintaining two lists: (1) for access information to
other accessible database repositories and (2) for access information
to accessible implementations of learning/related systems. Please let
me know if you have additions to these lists. Although I am not aware
of accessible software repositories and don't have the time to maintain one,
this should at least be a start towards centralizing access information.
David Aha
aha@ics.uci.edu
UCI repository access: ics.uci.edu ~/pub/machine-learning-databases
(userid & password "anonymous")
======================================================================
Quick Listing of the Repository's Contents:
1. annealing (David Sterling and Wray Buntine)
2. audiology (Ray Bareiss and Bruce Porter, used in Protos)
3. autos (Jeff Schlimmer)
4. breast-cancer (Ljubljana Institute of Ontcology, restricted access)
5. bridges (Yoram Reich)
6-13. chess
1. Partial generator of Quinlan's chess-end-game data (kr-vs-kn) (Schlimmer)
2. Shapiros' endgame database (kr-vs-kp) (Rob Holte)
3-8. Six domain theories (Nick Flann)
14. Ein-Dor and Feldmesser's cpu-performance database (David Aha)
15. Nine small EBL domain theories and examples in sub-directory ebl
16. Evlin Kinney's echocardiogram database (Steven Salzberg)
17. flags (Richard Forsyth)
18. function-finding (Cullen Schafer's 352 case studies)
19. glass (Vina Spiehler)
20. hayes-roth (from Hayes-Roth^2's paper)
21-24. heart-disease (Robert Detrano)
25. hepatitis (G. Gong)
26. iris (R.A. Fisher, 1936)
27. kinship (J. Ross Quinlan)
28. labor-negotiations (Stan Matwin)
29-30. led-display-creator (from the CART book)
31. lenses (Cendrowska's database donated by Benoit Julien)
32. liver-disorders (BUPA Medical's database donated by Richard Forsyth)
33. logic-theorist (Paul O'Rorke)
34. lymphography (Ljubjana Institute of Oncology, restricted access)
35. mechanical-analysis (Francesco Bergadano)
36. molecular-biology
1. promoter sequences (Towell, Shavlik, & Noordewier, domain theory also)
37. mushroom (Jeff Schlimmer)
38. primary-tumor (Ljubjana Institute of Oncology, restricted access)
39. shuttle-landing-control (Bojan Cestnik)
40-41. soybean (from Ryszard Michalski's groups)
42. spectrometer (Infra-Red Astronomy Satellite Project Database, John Stutz)
43-50. thyroid-disease (Garavan Institute, J. Ross Quinlan)
51-65. Undocumented databases: sub-directory undocumented
1. flare database (Gary Bradshaw)
2. Pat Langley's data generator
3. Information retrieval (IR) data collection (offline, David Lewis)
4. Economic sanctions database (domain theory included, Mike Pazzani)
5. Latest version of the thyroid database (domain theory, J. Ross Quinlan)
6. Cloud cover images (Philippe Collard)
7. Horse colic (Mary McLeish & Matt Cecile)
8. Generator for creating structured objects ("animals", John Gennari)
9. DNA secondary structure (Qian and Sejnowski, donated by Vince Sigilitto)
10. Pima Indians diabetes diagnoses (Vince Sigilitto)
11. Ionosphere information (Vince Sigilitto)
12. Nettalk data (Sejnowski and Rosenberg, taken from connectionist-bench)
13. Sonar data (Gorman and Sejnowski, taken from connectionist-bench)
14. Protein folding data (see connectionist-bench)
15. Vowel data (Qian and Sejnowski, taken from connectionist-bench (see 9))
66. university (Michael Lebowitz, donated by Steve Souders)
67. voting-records (Jeff Schlimmer)
68-69. waveform domain (taken from CART book)
70. Zoological database (Richard Forsyth)
------------------------------
END of ML-LIST 2.15
