genetic-programming.org-Home-Page

Time 2020-09-12 08:04:51

Web Name: genetic-programming.org-Home-Page

WebSite: http://www.genetic-programming.org

ID:44246

Keywords:

programming,genetic,org,

Description:

Genetic programming (GP) is an automated method forcreating a working computer program from a high-level problem statement of aproblem. Genetic programming starts from a high-level statement of “what needsto be done” and automatically creates a computer program to solve the problem. There are now 36 instanceswhere genetic programming has automatically produced a result that iscompetitive with human performance, including  15 instances where genetic programming hascreated an entity that either infringes or duplicates the functionality of apreviously patented 20th-century invention, 6 instances wheregenetic programming has done the same with respect to a 21st-centryinvention, and 2 instances where genetic programming has created a patentablenew invention. Given these results, we say that “Genetic programming now routinely delivershigh-return human-competitive machine intelligence.” Click here for ourdefinitions of “human-competitive,”  ”high return” andthe “AI ratio” (“artificial-to-intelligence” ratio),  “routine,” and “machineintelligence.” This statement is the most important point of the 2003book GeneticProgramming IV: RoutineHuman-Competitive Machine Intelligence. Click here to read chapter 1 of GeneticProgramming IV in PDF format.  Click here for 2004 awards forhuman-competitive results (based on presentations at the GECCO-2004conference in Seattleon June 27, 2004).The fact that genetic programming can evolve entities that are competitivewith human-produced results suggests that geneticprogramming can be used as an automated invention machine to create newand useful patentable inventions. In acting as an invention machine,evolutionary methods, such as genetic programming, have the advantage of notbeing encumbered by preconceptions that limit human problem-solving to well-troden paths. Genetic programming has delivered a progression ofqualitatively more substantial results in synchrony with fiveapproximately order-of-magnitude increases in the expenditure of computer time(over the 15-year period from 1987 to 2002). Genetic programming has 16 important attributes that one would reasonablyexpect of a system for automaticprogramming (sometimes also called program synthesis or programinduction). Genetic programming has seven importantdifferences from conventional approaches to artificial intelligence(AI) and machine learning (ML). For additional information, click here for PowerPoint(PPT) presentation on genetic programming (about 5 Megabytes) similarto that presented at the 2003 Accelerating Change Conference on September 13,2003 and similar to the overview lecture given on September 24, 2003 in JohnKoza’s course at Stanford University on genetic algorithms (GA) and geneticprogramming (GP).Genetic programming starts with a primordial ooze of thousands of randomlycreated computer programs. This population of programs is progressively evolvedover a series of generations. The evolutionary search uses the Darwinianprinciple of natural selection (survival of the fittest) and analogs of variousnaturally occurring operations, including crossover (sexual recombination),mutation, gene duplication, gene deletion. Genetic programming sometimes alsoemploys developmental processes by which an embryo grows into fully developedorganism. Old Chinese saying says “animated gif is worth one mega-word,” so click herefor short tutorial of “What is GP?” including about two dozen animated gifs.This short tutorial contains a discussion of the preparatory stepsof a run of genetic programming, the executional steps (that is, the flowchart of geneticprogramming), an illustrativesimple run of genetic programming for a problem of symbolic regressionof a quadratic polynomial, a discussion of developmentalgenetic programming for the automatic synthesis of both the topologyand sizing of analog electrical circuits (potentially also including placementand routing), and the use of a turtle to draw complex structures (such asantenna). In addition, genetic programming can automatically create, in asingle run, a general (parameterized) solution to a problem in the form of agraphical structure whose nodes or edges represent components and where theparameter values of the components are specified by mathematical expressionscontaining free variables. That is, genetic programming can automaticallycreate a general solution to a problem in the form of a parameterizedtopology. Information about the Field of Genetic Programming (GP) and the Field ofGenetic and Evolutionary Computation (GEC)The technique of genetic programming (GP) is one of the techniques of thefield of genetic and evolutionary computation (GEC) which, in turn, includestechniques such as genetic algorithms (GA), evolution strategies (ES),evolutionary programming (EP), grammatical evolution (GE), and machine code(linear genome) genetic programming. 16 authored books, 4 videos, and 4 edited books on genetic programming (GP), including 6 books in the Genetic Programming Book series from Kluwer Academic Publishers (as part of the bigger list of 73 authored books, 32 edited books, and 4 videos on genetic and evolutionary computation). 17 conference proceedings books on genetic programming (GP), including the 3 annual GP conferences, 5 annual GECCO conferences (that now include the annual GP conference), 6 annual Euro-GP conferences, the 2003 Genetic Programming Theory and Practice workshop (GPTA), the 1995 AAAI Symposium on Genetic Programming, and the 1995 Workshop on Genetic Programming (as part of a bigger list of 99 conference proceedings books on evolutionary computation). 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 Over 4,000 published papers on evolutionary computation in a searchable bibliography maintained by Karsten Weicker and Nicole Weicker containing entries on genetic and evolutionary computation and related areas (e.g. artificial life). About two dozen conferences with Published Proceedings that are held regularly in the field of genetic programming and genetic and evolutionary computation (GEC) $5,000 in 2004 awards for human-competitive results (based on presentations at the GECCO-2004 conference in Seattle on June 27, 2004). $10,000 in 2005 awards for human-competitive results (deadline for entry: June 20, 2005) E-Mail Mailing List on Genetic Programming, the EC-Digest (formerly the GA-Digest), and other mailing lists. Genetic Programming and Evolvable Machines journal (published by Kluwer Academic Publishers and edited by Wolfgang Banzhaf) (started January 2000). This journal is available as part of membership in the International Society for Genetic and Evolutionary Computation (ISGEC) Evolutionary Computation journal (published by The MIT Press and edited by Marc Schoenauer). This journal is available as part of membership in International Society for Genetic and Evolutionary Computation (ISGEC) IEEE Transactions on Evolutionary Computation journal (published by IEEE Neural Network Society and edited by Xin Yao) Software for genetic programming, genetic algorithms, and other evolutionary computation techniques, including the Little LISP Computer Code for Genetic Programming as Contained in 1992 book Genetic Programming (Koza 1992) 37 completed Ph.D. theses on genetic programming 58 students working on thesis involving genetic programming A partial list of people compiled by Bill Langdon who are active in genetic programming International Society for Genetic and Evolutionary Computation (ISGEC). ISGEC is the only membership organization in the field of genetic and evolutionary computation. It operates of the annual GECCO conference (largest conference in the field of genetic and evolutionary computation) and the biannual FOGA conference. Evo-Net —The Network of Excellence in Evolutionary Computation (an extensive clearinghouse of information about the field of genetic and evolutionary computation and operator of the annual Euro-GP conferences and the Evo-Net workshops) The GA Archives, including back issues of the GA-Digest and EC-Digest, genetic algorithm code in various programming languages, an extensive list of conference announcements in the field of genetic and evolutionary computation, etc. Book series of genetic programming for Kluwer Academic Publishers book series on genetic programming, edited by John R. Koza Book series on genetic algorithms and evolutionary computation from Kluwer Academic Publishers, edited by David E. Goldberg. Courses (and short courses) at various universities on genetic algorithms, genetic programming, and evolutionary computation For information about John Koza’s course on genetic algorithms and genetic programming at Stanford University 11 Books of Student Papers from John Koza's Courses at Stanford University on genetic algorithms and genetic programming and artificial life 6 Course Readers from John Koza's courses at Stanford University on genetic algorithms and genetic programming and artificial life John Koza's home page at Stanford University For 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 (2003) in PDF format. 36 human-competitive results produced by genetic programming, including 21 previously patented inventions replicated by genetic programming and 2 patentable new inventions generated by genetic programming. Link to http://www.genetic-programming.COM (“genetic-programming.COM” WITH the hyphen) (Genetic Programming Inc.) including information about 1,000-Pentium parallel computer for doing genetic programming research. Jobs for scientific research programmer at Genetic Programming Inc. Link to Jaime Fernandez’s genetic programming notebook site (“geneticprogramming.com” WITHOUT the hyphen) David Beasley’s Frequently Asked Questions about genetic and evolutionary computation. This comes in 6 parts. Part 2 has a summary of the different types of genetic and evolutionary computation.Conferences about Genetic Programming (GP) and Genetic and EvolutionaryComputation (GEC) About two dozen conferences (in addition to those below) with Published Proceedings that are held regularly in the field of genetic programming and genetic and evolutionary computation (GEC) Annual 2005 Genetic and Evolutionary Computation (GECCO) conference to be held on June 25–29, 2005 (Saturday – Wednesday) in Washington DC. GECCO is the largest conference in the field of genetic and evolutionary computation. The GECCO-2005 conference is a combination of the 10th annual Genetic Programming Conference (GP-2005) and the 14th International Conference on Genetic Algorithms (ICGA-2005). GECCO is operated by the International Society for Genetic and Evolutionary Computation (ISGEC). Past GP conferences for 1996, 1997, and 1998 (including the SGA-98, the Symposium on Genetic Algorithms) Past Euro-GP conferences for 1998, 1999, 2000, 2001, 2002, and 2003 Past GECCO conferences (Genetic and Evolutionary Computation Conferences) for 1999, 2000, 2001, 2002, 2003, and 2004. Starting in 1999, the annual GECCO conference includes the annual Genetic Programming ConferenceFor May 2003 IEEE Intelligent Systems article “What’s AI done for melately? Genetic programming’s human-competitive results”, visit IEEE Intelligent Systems. Clickhere for PDFfile. For February 2003 Scientific American article “Evolving inventions” on geneticprogramming by John Koza, Martin A. Keane, and Matthew J. Streeter, visit ScientificAmerican.For Salonarticle on Software that Writes Software by Alexis Willihnganz (August10, 1999)For E.E. Times article on automatic synthesis of analogelectrical circuits using genetic programming.For article in Computerbits on genetic programming.For ScientificAmerican article by W. Wayt Gibbs ongenetic programming. For Business Week article (June23, 1997) entitled Stanford Eggheads and Entrepreneurs For Business Week article(August 25, 1997) entitled What Matters is How Smart YouAre For U. S. Newsand World Report article on evolutionary computation and geneticprogramming. For Slashdot.orgposting (August 10, 1999). For the451.comarticle entitled Re-inventing the 'invention machine (April 14, 2000). “black art” problems, such as the automated synthesis of analog electrical circuits, controllers, antennas, networks of chemical reactions, and other areas of design, “programming the unprogrammable” (PTU) involving the automatic creation of computer programs for unconventional computing devices such as cellular automata, multi-agent systems, parallel systems, field-programmable gate arrays, field-programmable analog arrays, ant colonies, swarm intelligence, distributed systems, and the like, “commercially usable new inventions” (CUNI) involving the use of genetic programming as an automated invention machine for creating commercially usable new inventions, and We are constantly looking for new domain areas in which to apply thetechniques of genetic programming to achieve human-competitive machineintelligence.In July 1999, Genetic Programming Inc. started operating a new 1,000-nodeBeowulf-style parallel cluster computer consisting of 1,000 Pentium II 350 MHzprocessors and a host computer. Click here for technical discussion of parallel geneticprogramming and building the 1,000-PentiumBeowulf-style parallel cluster computer. About half of the 36human-competitive results produced by genetic programming were obtained using computingsystems that were substantially smaller than the 1,000-Pentium computermentioned above. Fifteen of these human-competitive results were obtained on a1995-vintage parallel computer system composed of 64 PowerPC 80 MHz processorswith a spec95fp rating. This 1995-vintage computer has total computationalpower equal to only about 1/60 of that of the 1000-Pentium machine mentionedabove. Five of these results were obtained on a 70-Alpha machine (whosespec95fp rating is 1/9 of that of the 1,000-Pentium machine mentioned above).One of these human competitive results were obtainedwith a 1994-vintage machine (whose spec95fp rating is 1/1,320 of that of the1,000-Pentium machine mentioned above). The individual processors in the1,000-Pentium machine have (as of July 2003) about 1/8 thespeed of processors contained in commercially available $999 laptops, so thatthe 1,000-Pentium machine is approximately equivalent to a 125-processormachine with 2003-vintage processors. 1000-Pentium Beowulf-Style ClusterComputer(left andright sides) (July 29, 1999) For picture ofuninterruptable power supply (UPS)for new 1000-Pentium computer. Design and contractingof site for 1000-Pentium computer by GordonPrill Inc. of Mountain View, California.The 1,000-Pentium machine was assembled by Stan Fox of the COMPAQ Sunnyvale Staging Center.For picture of earlier 70-node parallel computer with SenatorBarbara Boxer (California), John Koza (back row), Oscar Stiffelman(front row), Forrest H Bennett III, and William Mydlowec. Forpicture of earlier 70-node parallel computer with EllenGoldberg (President of Santa Fe Institute), John Koza, Forrest HBennett III, and Oscar Stiffelman. 1992 book on genetic programming entitled Genetic Programming: On the Programming of Computers by Means of Natural Selection from The MIT Press. The MIT Press also publishes a videotape entitled Genetic Programming: The Movie associated with the first book. Click here for more information about this 1992 videotape. 1994 book on genetic programming entitled  Genetic Programming II: Automatic Discovery of Reusable Programs from The MIT Press. The MIT Press also publishes a videotape entitled Genetic Programming II Videotape: The Next Generation. associated with this second book. Click here for additional information about this 1994 videotape. 1999 book Genetic Programming III: Darwinian Invention and Problem Solving from Morgan Kaufmann (by John R. Koza, Forrest H Bennett III, David Andre, and Martin A. Keane). Morgan Kaufmann also publishes Genetic Programming III Videotape: Human-Competitive Machine Intelligence (by John R. Koza, Forrest H Bennett III, David Andre, Martin A. Keane, and Scott Brave). Click here for information about this 1999 videotape. 2003 book Genetic Programming IV: Routine Human-Competitive Machine Intelligence from Kluwer Academic Publishers (by John R. Koza, Martin A. Keane, Matthew J. Streeter, William Mydlowec, Jessen Yu, and Guido Lanza ) (ISBN 1-4020-7446-8) Kluwer Academic Publisher also publishes a DVD disk Genetic Programming IV: Video: Routine Human-Competitive Machine Intelligence (by John R. Koza, Martin A. Keane, Matthew J. Streeter, William Mydlowec, Jessen Yu, Guido Lanza, and David Fletcher) that is bound into this 2003 book. Stanford University technical reports from the Computer Science Department and Stanford BioMedical Informatics of which I am author or co-author can be obtained on the web, including STAN-TR-CS 1314 (1990) entitled Genetic Programming: A Paradigm for Genetically Breeding Populations of Computer Programs to Solve Problems STAN-TR-CS 1528 (1994) entitled Architecture-Altering Operations for Evolving the Architecture of a Multi-Part Program in Genetic Programming STAN-TR-CS 1542 (1995) entitled Parallel Genetic Programming on a Network of Transputers SMI-95-0586 (1995) entitled A Programming Course in Bioinformatics for Computer and Information Science Students SMI-2000-0851 (2000) entitled Reverse Engineering and Automatic Synthesis of Metabolic Pathways from Observed Data Using Genetic Programming· For information about the annual Genetic and EvolutionaryComputation Conference (GECCO) operated by the Association for Computing SpecialInterest Group on Genetic and Evolutionary Computation (SIGEVO)· For information about theannual Human-Competitive Awards (the “humies”) in genetic and evolutionary computationoffered at the annual Genetic and Evolutionary Computation Conference (GECCO)· The homepage of Genetic Programming Inc. at www.genetic-programming.com.· The home page of John R. Koza (including onlineversions of most published papers)For information about John Koza’s course on geneticalgorithms and genetic programming at Stanford UniversityFor information about National Popular Vote · Information about the 1992book GeneticProgramming: On the Programming of Computers by Means of Natural Selection,the 1994 book GeneticProgramming II: Automatic Discovery of Reusable Programs, the 1999book GeneticProgramming III: Darwinian Invention and Problem Solving, and the2003 book GeneticProgramming IV: Routine Human-CompetitiveMachine Intelligence. Click here to read chapter 1 of GeneticProgramming IV book in PDF format. · 4,000+published papers on genetic programming (as of November 28, 2003) in asearchable bibliography (with many on-line versions of papers) by over 880authors maintained by William Langdon’s and Steven M. Gustafson. · For information on the Genetic Programming andEvolvable Machines journal · For information on theGenetic Programming book series, see the Call ForBook Proposals

TAGS:programming genetic org 

<<< Thank you for your visit >>>

Hot Websites