Ryszard S. Michalski
(1937 - 2007)
PRC Chaired Professor of Computational Sciences
and Health Informatics
Director of the Center for Discovery Science and Health Informatics
George Mason University
|
|
This page has been visited
since January 1, 1999
Articles in Mason Gazette:
7/31/07 |
New Center to Help Investigators Discover New Knowledge in Medical Databases
|
3/12/03 |
University Wins 10th Patent for Machine Learning Invention
|
11/19/02 |
Spotlight on Research: Grants Support Machine Learning and Inference Research
|
7/27/00 |
Michalski Receives Prestigious Science Honor
|
- Research areas:
-
Machine Learning,
Data Mining and Knowledge Discovery,
Inductive Databases and Knowledge Scouts,
Non-Darwinian Evolutionary Computation and
Plausible Reasoning,
and applications of these areas to Bioinformatics, Medicine, User Modeling, Intrusion Detection, and Very Complex System Design.
-
Other:
-
Natural nutrition, conventional and alternative medicine, hiking, skiing
(I am a former ski instructor and my wife skies even better--
if you will have an unattended villa or condo in the mountains next winter--do
not forget to let us know), tennis (if you are going to visit us, remember to take your tennis shoes),
piano and accordion playing (because of my teaching and research duties, I will not be able to play at your wedding,
but I play sometimes for senior citizens, my wife, and friends who are musically not too demanding),
and international humor--I will treat you with a special non-toxic drink for a good joke.
Ryszard S. Michalski
is Planning Research
Corporation Chaired
Professor of Computational Sciences, and Director of the GMU Machine
Learning
and Inference Laboratory. He is also a Foreign Member of the Polish
Academy
of Sciences, Fellow of AAAI, and Affiliate Scientist at the Institute
of Computer Science in Warsaw.
Dr. Michalski is a
cofounder of the field of machine learning, and the originator of
several research
subareas, such as conceptual clustering, constructive induction,
variable-valued logic, natural induction,
variable-precision logic (with Patrick Winston, MIT), computational
theory of human plausible reasoning (with Alan Collins from
BBN, Cambridge, MA), two-tiered representation of imprecise
concepts, multistrategy task-adaptive learning, inferential theory
of learning, learnable evolution model, and, most recently, inductive
databases and knowledge scouts.
Dr. Michalski's educational background includes studies at the Cracow and
Warsaw Universities of Technology, an M.S. degree from St. Petersburg
Polytechnical University, and a Ph.D. degree from the Silesian University of
Technology. Before emigrating to the United States in 1970,
he was a research scientist at the Polish Academy of Sciences. From 1970 to
1987, Dr. Michalski was on the faculty of the Computer Science
Department at the University of Illinois at Urbana-Champaign, initially
as a Research Professor, and then as Full Professor of Computer
Science and Medical Information Science, and Director of Artificial
Intelligence Laboratory. In 1988, he moved with his research group
to George Mason University in Fairfax, VA
(Washington, D.C. metropolitan area).
Dr. Michalski's first major
project was the development (in collaboration with Jacek Karpinski, Polish Academy of Sciences)
of an early successful learning system for recognizing handwritten
alpha-numeric characters. He then invented algorithm AQ for
solving the general covering problem (it was his third Ph.D. thesis),
which subsequently became a basis for many machine learning programs,
and remains
an exciting topic for modern machine learning research. He originated
research on constructive induction and conceptual clustering; developed
a
computational theory of
inductive learning; introduced variable-valued logic; and co-developed
a computational theory of human plausible reasoning. Collaborating with James Sinclair, a plant
pathologist at the University of Illinois, he
developed the first
agricultural expert system, and the first practical expert system that
learned its
decision rules from examples (1977). He also developed the inferential
theory of learning (ITL), which views every form of learning as a
process of
increasing the agent's knowledge through an application of knowledge
operators (transmutations). Recently, he introduced a form of
non-Darwinian evolutionary computation, called Learnable Evolution
Model (LEM), in which evolutionary process is guided by machine
learning. Early papers and proposals on LEM were rejected by reviewers
because they did not believe that LEM can speed-up evolution by two or
more orders of magnitude, but the most recent proposal received an
unanimous acclaim.
Dr. Michalski
cofounded Journal of Machine Learning, and
coorganized the first several international machine learning
conferences. He has lectured extensively
worldwide, and held visiting professorships at major universities in
the U.S., including MIT,
CMU and the University of Wisconsin, as well as abroad, specifically,
in Belgium, Germany, Great Britain, Italy, France, and Poland.
His current
research concerns natural induction (learning human-oriented
knowledge), learnable evolution model, knowledge mining (mining human-oriented knowledge from data and prior knowledge),
inductive databases and knowledge scouts (a new approach to minting human-oriented
knowledge from data and prior knowledge), and user modeling (profiling
computer user activities for intrusion and fraud detection).
He authored/co-authored/co-edited 16 books/proceedings and over 350 research
publications.
Selected Recent Presentations
Presentation on "Selected Applications of Natural Induction and Conceptual Clustering," IRS, April 27, 2006.
Invited presentation on "Non-Darwinian Evolutionary Computation: Guiding Evolution by Machine Learning,"
Center for Automated Learning and Discovery, Carnegie-Mellon University, February 11, 2004.
Invited presentation on "Inferential Theory of Learning and Natural Induction,"
at the UQAM Summer Institute in Cognitive Sciences, Montreal, June 30th-July 11th, 2003.
Advanced Seminar on Machine Learning and Inference
Advanced Topics in Artificial Intelligence
Advanced Topics in Data Mining and Knowledge Discovery
Computational Learning and Discovery
Computer Inference and Knowledge Acquisition
Computer Programming
Concept Learning and Natural Induction
Data Analysis and Knowledge Discovery
Data Bases
Data Mining and Knowledge Discovery
Data Structures
Information Systems
Introduction to Artificial Intelligence
Knowledge-based Systems
Logic Programming
Machine Learning
Pattern Recognition
Principles of Knowledge Mining
Principles of Machine Learning and Inference
Learning system for handwritten character recognition (1966)
General Logic Diagram for representing discrete functions (1966)
Star methodology for solving the general covering problem (1969)
Aq algorithm (1969)
Method for minimizing symmetric logic functions (1969)
Variable-valued logic, and systems VL1 and VL2 (1971, 72)
Internal disjunction and conjunction (1972)
AQVAL (AQ 1) symbolic learning system (1972)
Lexicographic Evaluation Functional-LEF (1973)
Inductive generalization rules (1976)
INDUCE learning methodology (1977)
Constructive induction (1978)
Qualitative prediction-SPARC (1979)
Conceptual clustering (1980)
Theory and methodology of inductive learning (1982)
Postulate of comprehensibility (1982)
Annotated predicate calculus (1982)
Variable-precision logic-with Patrick Winston (1984)
Multistrategy learning (1984)
Qualitative Prediction (1985)
Personal learning and inference system-Aurora (1986)
Two-tiered concept representation (1987)
Dynamic recognition (1987)
Logic of human plausible reasoning-with Alan Collins (1979-1989)
Illian/Emerald: Robots that Learn and Discover,
a system presented at the national exhibit
"ROBOTS AND BEYOND: Age of Intelligent Machines"
that toured major U.S. museums of science (1987/90)
Multistrategy data mining/Knowledge segment (1991)
Dynamic Interlaced Hierarchies (1991)
Data-driven constructive induction (1991)
Hypothesis-driven constructive induction (1991)
Inferential theory of learning (1991)
Knowledge transmutations (1991)
Multistrategy task-adaptive learning (1991)
Multistrategy constructive induction (1992)
Learning trees from rules (1993)
Compact decision trees (1993)
Significance vector method (1966/1996)
Natural induction (1996)
Learnable Evolution Model-LEM (1997)
Data Inferencing (1998)
Inductive databases (1977/99)
Knowledge scouts (1999)
Adaptive anchoring discretization (2000)
Knowledge Mining (2001)
Concept Association Graphs (2001)
Prediction-based User Models (2002)
Attributional Ruletrees (2002)
Multistate Template User Models (2003)
Method for generating alternative hypotheses (2003)
iAQ (1986/2004)
Attributional calculus (1998/2004)
Method for reasoning with meta-values--with Janusz Wojtusiak (2004)
Estimating Rule Coverages from Selector Coverages in Rule Learning (2004)
The LEMd methodology for designing very complex systems--with Ken Kaufman (2005)
Learning with compound attributes--with Janusz Wojtusiak (2005)
Generalizing Data in Natural Language--with Janusz Wojtusiak (2006)
By clicking on "Publications" above you will be able to see Dr. Michalski's publications either arranged into categories or listed yearwise. If you click on "MLI Publications" you will see all publications of the Machine Learning and Inference Laboratory.
Ryszard Solving Problems (with difficulty)
Reaching the top of a mountain may give you a similar feeling as solving a research problem, but
you may also experience a spectacular view.
|
|
|
|
Copyright © 2005 Machine Learning and Inference Laboratory