Entries are hereby solicited for awards totaling $10,000 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 the deadline for the previous competition and the deadline for the current competition.
The competition will be held as part of the 2014 Genetic and Evolutionary Computation (GECCO) conference. Presentations of entries will be made at the conference. The awards and prizes will be announced and presented during the conference. See http://www.sigevo.org/gecco-2014/
If you plan to make an entry for this competition, please check the web site at www.human-competitive.org for updated information prior to submitting your entry. If you make an entry, please re-check this web site periodically prior to the conference for additional (and possible changing) information and instructions.
The judging committee:
Techniques of genetic and evolutionary computation are being increasingly applied to difficult real-world problems — often yielding results that are not merely academically interesting, but competitive with the work done by creative and inventive humans. Starting at the Genetic and Evolutionary Computation Conference (GECCO) in 2004, cash prizes have been awarded for human-competitive results that had been produced by some form of genetic and evolutionary computation in the previous year.
This prize competition is based on published results. The publication may be a paper at the GECCO conference (i.e., regular paper, poster paper, or any other full-length paper), a paper published anywhere in the open literature (e.g., another conference, journal, technical report, thesis, book chapter, book), 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 without any further changes). The publication may not be an intermediate or draft version that is still subject to change or revision by the authors or editors. The publication must meet the usual standards of a scientific publication in that it must clearly describe a problem, the methods used to address the problem, the results obtained, and sufficient informationabout how the work was done in order 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.
Contestants should note that a pervasive thread in most of the above eight criteria is the notion that the result satisfy an "arms length" standard — not a yardstick based on the opinion of the author, the author's own institution (educational or corporate), or the author's own close associates. "Arms length" may be established in numerous ways. For example, if the result is a solution to "a long-standing problem forwhich 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 previously patented invention, constitutes a patentable new invention, or replicates or improves a resultthat 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 each of the foregoing examples, the standard for human-competitiveness is being established external to the author, the author's own institution, or the author's close associates. It is also conceivable to rely only on criterion G ("The result solves a problem of indisputable difficulty in its field"); however, if only criterion G is claimed, there must be a clear and convincing argument that the problem's "difficulty" is indeed "indisputable."
The competition will be held as part of the annual Genetic and Evolutionary Computation (GECCO) conference. Presentations of entries are to be made at the conference. The awards and prizes will be announced at the conference.
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 one or more of 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. Prizes are paid by check in U.S. dollars.
If you plan to make an entry into this competition, please check the web site at www.human-competitive.org for updated information prior to submitting your entry. If you make an entry, please re-check the web site prior to the conference for possible changes in the instructions or the schedule.
All entries are to be sent electronically to koza at human-competitive dot org
. All entries will be promptly acknowledged, so please make an inquiry if you do not receive a prompt acknowledgment.
An entry must consist of one TEXT file and one or more PDF files. If the same authors are making multiple entries, please submit separate e-mails, each containing both the requiredTEXT and PDF file(s) supporting the entry.
The TEXT file must contain the following 10 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. The papers and presentations from earlier competitions (starting in 2004) are posted at the competition web site at www.human-competitive.org and may be informative.
The PDF file(s) are to contain the paper(s). The strongly 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, conferenceattendees, and anyone else who is interested) and will remain posted on the web as a permanent record of the competition. If your paper is only available on the publisher's web site and your publisher specifically requires that your published paper may 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 general home page, but a link to the specific web page containing your paper on the publisher's site). The objective, in each case, is to provide a permanent record of the entries and to make it easy for anyone to locate the entries.
Generally, only one paper should be submitted. Note that this is a competition involving a result that satisfies the criteria for being human-competitive (not a competitioninvolving an author's entire body of work). More than one paper should be submitted only if no one paper fullydescribes the result or methods.
The judging committee will review all entries and identify a short list of approximately 6–10 finalists for presentation at the GECCO conference. Finalists will be notified by an e-mail to the corresponding author. Please acknowledge receipt of this message, so the judges know that you received your notice. Finalists must then make a short oral presentation to the judging committee at a public session of the GECCO conference. The presentations will be held on one of the early days of the conference and the winners will be announced a day or two later.
Finalists must submit their presentation (e.g., a PowerPoint, PDF) by e-mail to koza at human-competitive dot org
. All submissions will be promptly acknowledged, so please make an inquiry if you do not receive a prompt acknowledgment. These presentations will be added to the web page for the competition.
At the GECCO conference, there will be 10-minute oral presentations by the finalists to the judging committee. The presentations will be open to all conference attendees at a special session of the conference. The oral presentation should primarily focus on
In the short oral presentation to the judges, a description of the work itself is decidedly secondary. By the time of the presentation the judges will be familiarwith the papers. Thus, the focus of the presentation is on reasons why the work being presented should win a prize — not an explanation or presentation of the work itself. In the unlikely event that a presenter is scheduled to make a presentation elsewhere at the GECCO conference at the same time, please notify the judging committee, so they can rearrange time slots. After the oral presentations, the award committee will meet and consider the presentations.
The presenting author for each entry must register for the GECCO conference.
A judge will recuse himself or herself if he or she is closely associated with a finalist (e.g., a current academic advisor, current collaborator, co-author with the finalistof related work).
Additional information is at www.human-competitive.org.