CALL FOR ENTRIES FOR 2004
HUMIES
$5,000 in PRIZES AT
THE 1st ANNUAL (2004) “HUMIES” AWARDS
FOR HUMAN-COMPETITIVE RESULTS
PRODUCED BY GENETIC AND EVOLUTIONARY COMPUTATION
HELD AT THE
GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE (GECCO)
IN
Last updated September 16, 2004
Recent years have seen significant growth in the theoretical foundations of
the field of genetic and evolutionary computation, as evidenced by an
increasing number of books on the theory of genetic algorithms and the theory
of genetic programming, the proceedings of the Foundations of Genetic
Algorithms (FOGA) and Genetic Programming Theory and Applications (GPTP)
workshops, and the proceedings of numerous general conferences in the field, such
as GECCO. At the same time, the techniques of genetic and evolutionary
computation are being increasingly adopted by industry to solve difficult
real-world problems. One aspect of the progress in the field of genetic and
evolutionary computation is the generation of human-competitive results.
Entries are hereby solicited for awards totaling $5,000 for
human-competitive results that have been produced by any form of genetic and
evolutionary computation and that have been published in the open literature
since July 1, 2003. A special session will be held at the Genetic and
Evolutionary Computation Conference (GECCO) in
The prize fund will be divided, as the committee decides, among the entries.
Every new result deemed by the committee to be human-competitive for the past
year will get some cash award. Depending on the committee’s evaluation of the
relative merit of the entries, the prize fund may be divided equally or may be
divided so as to reflect a ranking among the results deemed to be
human-competitive. The committee may
Authors are encouraged to nominate their own work. Anyone may call the
committee’s attention to particular work by
Entries must be submitted by e-mail by 5 PM Pacific time on Monday June 21,
2004. An entry consists of
(1)
the name, physical address, e-mail address, and phone
number of EACH author,
(2)
the title of at least one paper published in the open
literature describing the work,
(3)
the abstract of the paper(s),
(4)
PDF file of the paper(s), and
(5)
a statement specifically identifying one or more of
the eight criteria (below) and stating why the result satisfies that criteria.
See examples (below) illustrating the form of the statement, and
(6)
a full citation of the paper (i.e., publisher, city,
date, editor names, if any, etc.)
One of the committee members (John Koza) has been designated as secretary
and is available to answer questions and offer advice on constructing entries
(and will, consequently, not vote during the committee’s deliberations).
Entries should be sent to
koza@genetic-programming.com.
At least one author of the paper must be present to
The full awards committee is currently in formation and its membership will
be announced. A committee member will not vote on a particular entry if he or
she is associated with that entry (e.g., academic advisor, collaborator,
co-author, working at the same institution). No cash prize may be awarded to
anyone employed by the company providing the prize funds (i.e., Third
Millennium Inc.); however, such person’s participation in a result will be
noted.
It is anticipated that similar awards may be made at GECCO-2005 in
COMMITTEE
Wolfgang
Banzhaf
David
E. Goldberg
Erik
D. Goodman
Riccardo
Poli
John
R. Koza (Secretary)
APPENDIX—EIGHT CRITERIA FOR
HUMAN-COMPETITIVENESS
For purposes of the awards, an automatically created result is
“human-competitive” if it satisfies one or more of the eight criteria below.
(A) The result was patented as an invention in the past, is an improvement
over a patented invention, or would qualify today as a patentable new
invention.
(B) The result is equal to or better than a result that was accepted as a
new scientific result at the time when it was published in a peer-reviewed
scientific journal.
(C) The result is equal to or better than a result that was placed into a
database or archive of results maintained by an internationally recognized
panel of scientific experts.
(D) The result is publishable in its own right as a new scientific
result—independent of the fact that the result was mechanically created.
(E) The result is equal to or better than the most recent human-created
solution to a long-standing problem for which there has been a succession of
increasingly better human-created solutions.
(F) The result is equal to or better than a result that was considered an
achievement in its field at the time it was first discovered.
(G) The result solves a problem of indisputable difficulty in its field.
(H) The result holds its own or wins a regulated competition involving human
contestants (in the form of either live human players or human-written computer
programs).
SOME EXAMPLES “STATEMENTS” OF
HUMAN-COMPETITIVENESS
CRITERIA A & F
Harry Jones of The Brown Instrument Company of
(A) The result was patented as an invention in the past, is an improvement
over a patented invention, or would qualify today as a patentable new
invention.
(F) The result is equal to or better than a result that was considered an
achievement in its field at the time it was first discovered.
The rediscovery by genetic programming of the PID-D2 controller came about
six decades after Jones received a patent for his invention. Nonetheless, the
fact that the original human-designed version satisfied the Patent Office’s
criteria for patent-worthiness means that the genetically evolved duplicate
would also have satisfied the Patent Office’s criteria for patent-worthiness
(if only it had arrived earlier than Jones’ patent application).
CRITERIA B, D, E, F & G
The 1942 Ziegler-Nichols tuning rules for PID controllers were a significant
development in the field of control engineering. These rules have been in
widespread use since they were invented.
The 1995 Åström-Hägglund tuning rules were another significant development.
They outperform the 1942 Ziegler-Nichols tuning rules on the industrially
representative plants used by Åström and Hägglund. Åström and Hägglund
developed their improved tuning rules by applying mathematical analysis,
shrewdly chosen approximations, and considerable creative flair.
The genetically evolved PID tuning rules are an improvement over the 1995
Åström-Hägglund tuning rules.
Referring to the eight criteria for establishing that an automatically
created result is competitive with a human-produced result, the creation by
genetic programming of improved tuning rules for PID controllers satisfies the
following five of the eight criteria:
(B) The result is equal to or better than a result that was accepted as a
new scientific result at the time when it was published in a peer-reviewed
scientific journal.
(D) The result is publishable in its own right as a new scientific
result—independent of the fact that the result was mechanically created.
(E) The result is equal to or better than the most recent human-created
solution to a long-standing problem for which there has been a succession of
increasingly better human-created solutions.
(F) The result is equal to or better than a result that was considered an
achievement in its field at the time it was first discovered.
(G) The result solves a problem of indisputable difficulty in its field.
EXAMPLE OF SOMETHING THAT MAY
BE DIFFICULT, BUT NOT HUMAN-COMPETITIVE
Although the solution produced by genetic programming for this problem is, in fact, better than a human-produced solution, that fact alone does not qualify the result as “human-competitive” under the eight criteria for human-competitiveness. The fact that a problem appears in a college textbook is not alone sufficient to establish the problem’s difficulty or importance. A textbook problem might, or might not, satisfy one or more of the eight criteria.
· The home page of Genetic Programming Inc. at www.genetic-programming.com.
· For information about the field of genetic programming and the field of genetic and evolutionary computation, visit www.genetic-programming.org
· The home page of John R. Koza at Genetic Programming Inc. (including online versions of most published papers) and the home page of John R. Koza at Stanford University
· For information about John Koza’s course on genetic algorithms and genetic programming at Stanford University
· Information about the 1992
book Genetic
Programming: On the Programming of Computers by Means of Natural Selection,
the 1994 book Genetic
Programming II: Automatic Discovery of Reusable Programs, the 1999
book Genetic
Programming III: Darwinian Invention and Problem Solving, and the
2003 book Genetic
Programming IV: Routine
Human-Competitive Machine Intelligence. Click here to read chapter 1 of Genetic
Programming IV book in PDF format.
· 3,440
published papers on genetic programming (as of November 28, 2003) in a
searchable bibliography (with many on-line versions of papers) by over 880
authors maintained by William Langdon’s and Steven M. Gustafson.
· For information on the Genetic Programming and Evolvable Machines journal published by Kluwer Academic Publishers
· For information on the Genetic Programming book series from Kluwer Academic Publishers, see the Call For Book Proposals
· For
information about the annual 2005
Genetic and Evolutionary Computation (GECCO) conference (which includes
the annual GP conference) to be held on June 25–29, 2005 (Saturday – Wednesday)
in Washington DC and its sponsoring organization, the International Society for
Genetic and Evolutionary Computation (ISGEC).
For information about the annual
2005 Euro-Genetic-Programming Conference (and the co-located Evolutionary
Combinatorial Optimization conference and other Evo-Net workshops) to
be held on March 30 – April 1, 2005 (Wednesday-Friday) in