Human-competitive results produced by genetic programming

By John R. Koza. Genetic Programming and Evolvable Machines, 2010

341 citations recorded by the source corpus.

Genetic programming has now been used to produce at least 76 instances of results that are competitive with human-produced results. These human-competitive results come from a wide variety of fields, including quantum computing circuits, analog electrical circuits, antennas, mechanical systems, controllers, game playing, finite algebras, photonic systems, image recognition, optical lens systems, mathematical algorithms, cellular automata rules, bioinformatics, sorting networks, robotics, assembly code generation, software repair, scheduling, communication protocols, symbolic regression, reverse engineering, and empirical model discovery. This paper observes that, despite considerable variation in the techniques employed by the various researchers and research groups that produced these human-competitive results, many of the results share several common features. Many of the results were achieved by using a developmental process and by using native representations regularly used by engineers in the fields involved. The best individual in the initial generation of the run of genetic programming often contains only a small number of operative parts. Most of the results that duplicated the functionality of previously issued patents were novel solutions, not infringing solutions. In addition, the production of human-competitive results, as well as the increased intricacy of the results, are broadly correlated to increased availability of computing power tracked by Moore’s law. The paper ends by predicting that the increased availability of computing power (through both parallel computing and Moore’s law) should result in the production, in the future, of an increasing flow of human-competitive results, as well as more intricate and impressive results.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/b1e8ae36a9ea814e5d214d6f5c2abb42cc9f1793

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Automatic programming: The open issue? (2019, background): “Much success lies in the generation of single line functions through Genetic Programming’s application to Symbolic Regression (for example see [58]) and design, for example, in the generation of analogue circuits [33–35], robot morphology [25] and antennae [40].”
GenProg: A Generic Method for Automatic Software Repair (2012, background): “Although GP has solved an impressive range of problems (e.g., [19]), it has not previously been used either to evolve off-the-shelf legacy software or to patch realworld vulnerabilities, despite various proposals directed at automated error repair, e.g., [20].”
Interpretable Policies for Reinforcement Learning by Genetic Programming (2017, background): “Since then, the ﬁeld of GP has grown signiﬁcantly and has produced numerous results that can compete with human-produced results, including controllers, game playing, and robotics (Koza, 2010).”
From evolutionary computation to the evolution of things (2015, result): “The performance of evolutionary algorithms has also been compared to that of human experts, and there is now substantial and well-documented evidence of EAs producing measurably human-competitive results 55 .”
Evaluation in artificial intelligence: from task-oriented to ability-oriented measurement (2017, methodology): “Worst-case analysis (equation 1) is more common than average-case analysis (equation 3), although the latter has also become popular recently (Knuth, 1973; Levin, 1986; Goldreich and Vadhan, 2007).”