David Bingham Skalak
Visitor
Department of Computer Science
Cornell University
Ithaca, NY 14853-7501
email: skalak@cs.cornell.edu
map: Ithaca and the Cornell Campus
Biographical Sketch
I received a B.S. in mathematics summa cum laude from Union College (1976), an M.A. in
mathematics from Dartmouth
College (1979), a J.D. from Harvard Law School (1982), an
M.S. (1989) and a Ph.D. (1997) in computer science from the University
of Massachusetts at Amherst. I was a Fulbright Fellow at the University of Southampton, England,
and have studied at the University
of St. Andrews, St. Andrews,
Scotland.
I'm currently a Senior Data Mining Analyst with IBM.
My current research interests include instance-based and local
learning algorithms, classifier combination, case-based reasoning, AI
and law, and the application of machine learning algorithms and knowledge
discovery methods to equity
selection, money management and market timing.
Curriculum Vitae
Academic CV
CV detailing financial experience
Editorial Activity
Editorial Advisory Board, Journal of Computational
Intelligence in Finance, 1996--2000.
Selected Publications
- Instance Sampling for Boosted and Standalone Nearest Neighbor
Classifiers.
To appear, Instance Selection and Construction: A Data Mining
Perspective, edited by H.~Motoda and H.~Liu, published by Kluwer
Academic Publishers.
-
Prototype Selection for Composite Nearest Neighbor Classifiers.
Ph.D. dissertation. Dept. of Computer Science, Technical Report 96-89,
University of Massachusetts, Amherst, Massachusetts.
( postscript, 2464K ). Thesis
also available here.
( compressed postscript, 758K ).
- The Sources of Increased Accuracy for Two Proposed Boosting Algorithms.
Proceedings of the AAAI-96 Integrating Multiple Learned Models Workshop,
Portland, OR, American Association for Artificial Intelligence, Menlo Park, CA, 1996 ( compressed postscript, 67K ).
- Prototype Selection for Composite
Nearest Neighbor Classifiers.
Dissertation Proposal. Dept. of Computer Science, Technical
Report 95-74, University of Massachusetts, Amherst, Massachusetts.
(compressed postscript, 325K) . Abstract.
- Prototype and Feature Selection by
Sampling and Random Mutation Hill-Climbing Algorithms.
Proceedings of the Eleventh International Conference on Machine
Learning, pp. 293-301, New Brunswick, New Jersey, 1994.
( postscript, 153K ).
- Using a Genetic Algorithm
to Learn Prototypes for Case Retrieval and Classification.
Proceedings of the AAAI-93 Case-Based Reasoning Workshop (Technical Report
WS-93-01), pp. 64-69, Washington, D.C., American Assocation for Artificial
Intelligence, Menlo Park, CA, 1994.
( Binhexed Macintosh Microsoft Word file ).
Survival Guides
- How to
Succeed in Graduate School: A Guide for Students and Advisors
Marie desJardins, Crossroads 1.2, December, 1994, and Crossroads 1.3,
February, 1995.
( Excellent. Check out the references and the appendix entitled "How to
be a Terrible Thesis Advisor". Also available in other formats from
http://www.erg.sri.com/people/marie/papers/advice-summary . )
- A Ph.D. Is Not Enough: A Guide to Survival in Science
Peter J. Feibelman, Addison-Wesley, Reading, MA, 1993. ISBN 0-201-62663-2.
( Worth reading well before you receive your Ph.D. )
- Getting What You Came For: The Smart Student's Guide to Earning a
Master's or a Ph.D.
Robert L. Peters, Noonday Press, Farrar Straus and Giroux, New York, NY, 1992.
ISBN 0-374-52361-4.
( Don't let the hokey title deter you; this is a wonderful book. )
-
Notes on Presenting Theses
Aaron Sloman, unpublished manuscript, February, 1992.
( Read this before you start writing. Especially useful tips for
describing large computer programs. )
Other People and Places to Visit
-
Claire Cardie