$10,000 IN AWARDS—THE 2006 “HUMIES”—FOR
HUMAN-COMPETITIVE RESULTS
Last updated March 28, 2006
1.
THE 2006
“HUMIES” AWARDS—$10,000 IN PRIZES
Techniques of genetic and evolutionary computation are being increasingly applied to difficult real-world problems—often yielding results that are not merely interesting, but competitive with the work of creative and inventive humans. At the Genetic and Evolutionary Computation Conference (GECCO) in 2004, $5,000 in 2004 awards for human-competitive results were awarded for human-competitive results that had been produced by some form of genetic and evolutionary computation in the previous year. Similarly, at GECCO-2005, $10,000 in awards for 2005 human-competitive results were awarded.
Entries are now being solicited for awards totaling $10,000 for 2006 awards for human-competitive results that have been produced by any form of genetic and evolutionary computation (including, but not limited to genetic algorithms, genetic programming, evolution strategies, evolutionary programming, learning classifier systems, grammatical evolution, gene expression programming, differential evolution, etc.) and that have been published in the open literature between June 20, 2005 (the deadline for the previous competition) and the deadline for 2006 entries, namely Monday May 29, 2006. The competition will be held as part of the 2006 Genetic and Evolutionary Computation (GECCO) conference. This prize competition is based on published results. The publication may be a paper at the GECCO-2006 conference (i.e., regular paper, poster paper, or late-breaking paper), a paper published anywhere in the open literature (e.g., another conference, journal, technical report, thesis, book, book chapter), or a paper in final form that has been unconditionally accepted by a publication and is “in press” (that is, the entry must be identical to something that will be published imminently—not an intermediate or draft version that may be changed). The publication must meet the usual standards of a scientific publication. In particular, the publication must clearly describe a problem, the methods used, and the results obtained and must contain sufficient information to enable the work described to be replicated by an independent person.
An automatically created result is considered “human-competitive” if it satisfies at least one 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 ¾ 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).
Contestants should note that a pervasive thread in most of the above eight
criteria is the notion that the result meet an “arms length” standard—not a yardstick based on the opinion of the
author, the author’s own institution,
or the author’s close associates. “Arms length” may be established in numerous
ways. For example, if the result is a solution to “a long-standing
problem for which there has been a succession of increasingly better
human-created solutions,” it is clear that the scientific community (not the
author, the author’s own institution,
or the author’s close associates) have vetted the significance of the problem.
Similarly, a problem’s significance may be established if the result replicates
or improves upon a scientific result published in a peer-reviewed
scientific journal, replicates or
improves upon a patented invention, or replicates or improves a result
that was considered an achievement in its field at the time it was first
discovered. Similarly, , a problem’s
significance may be established if the result holds its own or wins a
regulated competition involving live human players or human-written computer
programs. In the absence of a clear “arms length” standards, contestants
relying only on criterion G (“The result solves a problem of indisputable
difficulty in its field”) must
Presentations of entries will be made at the Genetic and Evolutionary Computation Conference (GECCO-2006). The awards and prizes will be announced and presented during the GECCO conference. The judging committee is in formation and will include
· Wolfgang Banzhaf
· Erik Goodman
· Riccardo Poli
· John R. Koza
· Darrell Whitley
Cash prizes of $5,000 (gold), $3,000 (silver), and bronze (either one prize of $2,000 or two prizes of $1,000) will be awarded for the best entries that satisfy the criteria for human-competitiveness. The awards will be divided equally among co-authors unless the authors specify a different division at the time of submission.
2. ENTRIES IN THE 2006 “HUMIES” AWARDS
3. COMPETITION RESULTS
|
Prize |
Entry Number |
Authors |
|
Gold |
#5 |
Aggarwal et al |
|
Silver |
#6 |
Sastry et al |
|
Bronze (1) |
#2 |
Yao et al |
|
Bronze (2) |
#1 |
Olague et al |
4. INSTRUCTIONS FOR ENTERING THE 2006 “HUMIES” AWARDS
The deadline for 2006 entries is Monday May 29, 2006.
All entries are to be sent electronically to koza@stanford.edu.
An entry consists of one TEXT file and one or more PDF files.
The TEXT file must contain the following nine items. Please be very careful to include all required information. Contestants are alerted to the fact that items 6 and 9 are especially important and will be the main basis by which entries will be judged.
(1) the complete title of one
(or more) paper(s) published in the open literature describing the work that
the author claims describes a human-competitive result,
(2) the name, complete
physical mailing address, e-mail address, and phone number of EACH author of
EACH paper,
(3) the name of the
corresponding author (i.e., the author to whom notices will be sent concerning
the competition),
(4) the abstract of the
paper(s),
(5) a list containing one or
more of the eight letters (A, B, C, D, E, F, G, or H) that correspond to the
criteria (see above) that the author claims that the work satisfies,
(6) a statement stating why
the result satisfies the criteria that the contestant claims (see the examples
below as a guide to aid in constructing this part of the submission),
(7) a full citation of the
paper (that is, author names; publication date; name of journal, conference,
technical report, thesis, book, or book chapter; name of editors, if
applicable, of the journal or edited book; publisher name; publisher city; page
numbers, if applicable);
(8) a statement either that
“any prize money, if any, is to be divided equally among the co-authors” OR a
specific percentage breakdown as to how the prize money, if any, is to be
divided among the co-authors; and
(9) a statement stating why
the judges should consider the entry as “best” in comparison to other entries
that may also be “human-competitive.”
The PDF file(s) are to contain the paper(s). The preferred method is that you send a separate PDF file for each of your paper(s) relating to your entry. Both the text file and the PDF file(s) for each entry will be permanently posted on a web page shortly after the deadline date for entries (for use by the judges and anyone interested) and will remain posted on the web as a permanent record of the competition. If your paper is available on your publisher’s web site and your publisher specifically requires that your published paper may only appear only on your own personal page, the second choice is that you send link(s) to a separate web page on your web site containing link(s) to the PDF file(s) of the paper(s) that constitute your entry. This separate web page is to contain nothing else, so the interested parties may quickly locate your paper(s). If you use this second-choice option, you must also supply a link to a permanent web site maintained by your publisher where your specific paper may be viewed or purchased (that is, not a link merely to the publisher’s home page, but a link to your specific paper on the publisher’s site).
The judging committee will review all
entries and identify a short list approximately 8–10 finalists for presentation at the 2006 Genetic and Evolutionary
Computation (GECCO) conference to be held in
At the conference, there will be 10-minute oral presentations by the finalists before the judging committee. The presentations will be open to all conference attendees at a special session (2 hours). The oral presentation should primarily focus on why the result qualifies as being human-competitive and why the judges should consider the entry as “best” in comparison to other entries that may also be “human-competitive” since these are the two main standards by which entries will be judged by the judges. In this short presentation to the judges, a description of the work itself should be decidedly secondary. In other words, the focus is on why the work being presented should win a prize—not an explanation or presentation of the work itself. The presenting author for each entry must register for the GECCO conference. After the oral presentations, the award committee will meet and consider the presentations. The awards are will announced at the Wednesday July 12, 2006, morning plenary session at the GECCO conference. Finalists must submit a presentation in the form of a PowerPoint file or a PDF file by Thursday July 5, 2006 by e-mail to koza@stanford.edu. These presentations will be added to the web page for the competition so that the judging committee (and anyone else interested) may preview the presentations.
Authors generally enter their own work; however, a person may
No prize may be awarded to anyone associated with any member of the judging committee (e.g., academic advisor, collaborator, co-author of the work involved) or the company donating the prize funds (i.e., Third Millennium On-Line Products Inc.).
IMPORTANT DATES:
May 29, 2006 (Friday) — Entries (consisting of one TEXT file and one or more PDF files) are due by e-mail.
June 25, 2006 (Monday) — Finalists will be notified by e-mail
July 5, 2006 (Wednesday) — Finalists must submit their presentation to (e.g., PowerPoint, PDF) for posting on competition web site.
July 10 (Monday) — Date for
presentations before judging committee at public session at GECCO conference in
|
Time |
Entry Number |
Speaker |
|
1:45 |
|
Session Starts |
|
1:45-2:00 |
|
Introduction of judges and description of
competition |
|
2:00-2:10 |
#1 |
Olaque |
|
2:10-2:20 |
#2 |
Yao |
|
2:20-2:30 |
#3 |
Thong |
|
2:30-2:40 |
#4 |
Deb |
|
2:40-2:50 |
#5 |
Aggarwal |
|
2:50-3:00 |
#7 |
Wu |
|
3:00-3:10 |
#8 |
Iorio |
|
3:10-3:20 |
#6 |
Sastry |
|
3:20-3:25 |
|
Wrap-up |
July 12 (Wednesday) —
Announcement of awards at morning plenary session of GECCO conference in
5. EXAMPLE OF A “STATEMENT” USING CRITERIA A & F
This is an illustrative example of a “statement” as to which an entry in the competition should be considered to be “human-competitive.”
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).
6.
ADDITIONAL EXAMPLE OF A “STATEMENT” USING
CRITERIA B, D, E, F & G
This is another illustrative example of a “statement” as to which an entry in the competition should be considered to be “human-competitive.”
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.
7.
EXAMPLE OF SOMETHING THAT MAY BE “DIFFICULT,”
BUT NOT “HUMAN-COMPETITIVE”
Although the solution produced by genetic and evolutionary computation 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. For example, the fact that a problem appears in a college textbook is not alone sufficient to establish the problem’s difficulty or importance or “human-competitiveness.” A result is “human-competitive” if it satisfies one or more of the 8 criteria listed above. A textbook problem might, or might not, satisfy one or more of the eight criteria.
· For information about the
annual 2006 Genetic and
Evolutionary Computation (GECCO) conference (which includes the annual
Genetic Programming conference) to be held on July 8-12, 2006 (Saturday – Wednesday) in
· Click here for tables showing the 23 entries in 2004, the “statements” of “human-competitiveness,” and the slides for the presentations for the $10,000 in awards for 2005 human-competitive results
· Click here for tables showing the 11 entries in 2004, the “statements” of “human-competitiveness,” and the slides for the presentations for the $5,000 in awards for 2004 for human-competitive results.
· 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 Genetic Programming Inc. at www.genetic-programming.com.
· The home page of John R. Koza (including online versions of most published papers)
· 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.
· 4,000+
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