Genetic Programming Theory Practice 2003 Workshop (GPTP-2003)

The Center for the Study of Complex Systems (CSCS) at the University of Michigan hosted an invitation-only workhop:

Genetic Programming Theory and Practice
15-17 May, 2003.

This workshop focused on how theory can inform practice and what practice reveals about theory. The goal was to evaluate the state-of-the-art in genetic programming by discussing different theories and their value to practitioners of the art and to review problems and observations from practice that challenge existing theory.

This was a small, invitation-only workshop on the campus of the University of Michigan in Ann Arbor. The workshop format was informal with plenty of time for discussion. John Holland gave a keynote address, and John Koza presented the lead-off talk. Other keynote speakers included Stephen Freeland, (Dept of Biology, Univ of Maryland), and Lynne Ellyn (VP and CIO of DTE Energy). Below is the list of all papers presented at the Workshop, along with their authors and affiliations.

The papers below are being published as chapters in the following book:

Genetic Programming Theory and Practice
Rick Riolo and Bill Worzel (eds.)
Kluwer Publishers, Boston, MA. 2003

which is available as of 1 Nov 2003, e.g., at Kluwer's online pages.

Acknowledgements

We would like to gratefully acknowledge the contributions made by the following organizations:
which made this Workshop possible. We would also like to acknowledge the support of The Center for the Study of Complex Systems (CSCS) and its director, Carl Simon.

Please also visit the list of all GPTP workshops.

Workshop Talk titles, authors and schedule.

Thursday, 2003 May 15

Welcome and opening remarks.
Carl Simon
Director, Center for the Study of Complex Systems
Professor, Economics, Mathematics and School of Public Policy

Keynote: GA and GP, Past and Future: What do they share besides the G?
John Holland
Psychology, CSCS, University of Michigan.

Morning Session:

T2. The distribution of reversible functions is normal.
Bill Langdon.
University College, London, UK
A6. Automated Synthesis by Means of Genetic Programming of Complex Structures Incorporating Reuse, Hierarchies, Development, and Parameterized Toplogies.
John R. Koza1, Matthew J. Streeter2 and Martin A. Keane3
1Stanford University, Stanford, California
2Genetic Programming Inc., Mountain View, CA
3Econometrics Inc., Chicago, Illinois

Afternoon Session #1:

T8. Doing Genetic Algorithms the Genetic Programming Way.
Conor Ryan.
University of Limerick, Ireland
A7. Modularization by Multi-Run Frequency Driven Subtree Encapsulation.
Daniel Howard.
Software Evolution Centre, Malvern, UK

Afternoon Session #2:

T4. What Makes a Problem GP-Hard? A Look at How Structure Affects Content.
Jason M. Daida.
The University of Michigan, Ann Arbor, MI
A8. Using Software Engineering Knowledge to Drive Genetic Programming Design Using Cultural Algorithms.
David Ostrowski1, Robert G. Reynolds2.
1Ford Motor Company Scientific Research Laboratories, Dearborn, MI
2Wayne State University, Detroit, MI

Friday, 2003 May 16

Keynote: Stephen Freeland
Biological Sciences, Univ. of Maryland, BC.

Morning Session:

T1. Artificial Regulatory Networks and Genetic Programming.
Wolfgang Banzhaf.
University of Dortmund, Dortmund
A2. The Continuous Hierarchical Fair Competition Model for Sustainable Innovation in Genetic Programming.
Erik D. Goodman, Jianjun Hu.
Genetic Algorithm Research & Application Group (GARAGe) Michigan State University, East Lansing, MI

Afternoon Session #1:

T9. An Essay Concerning Human Understanding of Genetic Programming.
Lee Spector.
Cognitive Science
Hampshire College, Amherst, MA
A3. Classification of Gene Expression Data with Genetic Programming.
Joseph A. Driscoll1, Bill Worzel2, Duncan MacLean2.
1Middle Tennessee State University, Murfreesburo, TN
2Genetics Squared, Inc., Milan, MI

Afternoon Session #2:

T5. Probabilistic Model Building and Competent Genetic Programming.
Kumara Sastry, David E. Goldberg.
Illinois Genetic Algorithms Laboratory (IlliGAL), University of Illinois, Urbana, IL
A4. Industrial Strength Genetic Programming Empirical Modeling and Symbolic Regression via GP Integrated Methodologies, Best Practices, Lessons Learned.
Mark Kotanchek, Guido Smits, and Arthur Kordon.
Dow Chemical

Saturday, 2003 May 17

Keynote: Lynn Ellyn VP, CIO, DTEnergy

Morning Session:

T6. Operator Choice and the Evolution of Robust Solutions.
Terry Soule.
University of Idaho
A5. Hybrid GP-Fuzzy Approach for Reservoir Characterization With a Gentle Introduction to Oil Exploration and Production.
Tina (Gwoing) Yu, Davie Wilkinson, Deyi Xei.
ChevronTexaco Information Technology Company & ChevronTexaco Exploration and Production Technology Company, San Ramon, CA

Afternoon Session #1:

T3. Building Block Supply in Genetic Programming.
Kumara Sastry1, Una-May O'Reilly2, David E. Goldberg,3
1Dept. of Material Sc. & Eng., University of Illinois, Urbana, IL
2Artificial Intelligence Lab, Massachussetts Institute of Technology, MA
3Dept. of General Engineering, University of Illinois, Ubrbana, IL
4Dept. of Civil and Environmental Eng., University of Illinois, Urbana, IL
A1. Enhance Emerging Market Stock Selection: A Genetic Programming Approach.
Anjun Zhou.
State Street Global Advisors

Afternoon Session #2:

T10. A Probabilistic Model of Size Drift.
Justinian Rosca.

Wrap-Up Discussion