Neuro-guided genetic programming: prioritizing evolutionary search with neural networks

Created by W.Langdon from gp-bibliography.bib Revision:1.8120

@InProceedings{Liskowski:2018:GECCOa,

• author = "Pawel Liskowski and Iwo Bladek and Krzysztof Krawiec",
• title = "Neuro-guided genetic programming: prioritizing evolutionary search with neural networks",
• booktitle = "GECCO '18: Proceedings of the Genetic and Evolutionary Computation Conference",
• year = "2018",
• editor = "Hernan Aguirre and Keiki Takadama and Hisashi Handa and Arnaud Liefooghe and Tomohiro Yoshikawa and Andrew M. Sutton and Satoshi Ono and Francisco Chicano and Shinichi Shirakawa and Zdenek Vasicek and Roderich Gross and Andries Engelbrecht and Emma Hart and Sebastian Risi and Ekart Aniko and Julian Togelius and Sebastien Verel and Christian Blum and Will Browne and Yusuke Nojima and Tea Tusar and Qingfu Zhang and Nikolaus Hansen and Jose Antonio Lozano and Dirk Thierens and Tian-Li Yu and Juergen Branke and Yaochu Jin and Sara Silva and Hitoshi Iba and Anna I Esparcia-Alcazar and Thomas Bartz-Beielstein and Federica Sarro and Giuliano Antoniol and Anne Auger and Per Kristian Lehre",
• isbn13 = "978-1-4503-5618-3",
• pages = "1143--1150",
• address = "Kyoto, Japan",
• DOI = "doi:10.1145/3205455.3205629",
• publisher = "ACM",
• publisher_address = "New York, NY, USA",
• month = "15-19 " # jul,
• organisation = "SIGEVO",
• keywords = "genetic algorithms, genetic programming, ANN",
• abstract = "When search operators in genetic programming (GP) insert new instructions into programs, they usually draw them uniformly from the available instruction set. Preferring some instructions to others would require additional domain knowledge, which is typically unavailable. However, it has been recently demonstrated that the likelihoods of instructions occurrence in a program can be reasonably well estimated from its input-output behaviour using a neural network. We exploit this idea to bias the choice of instructions used by search operators in GP. Given a large sample of programs and their input-output behaviours, a neural network is trained to predict the presence of individual instructions. When applied to a new program synthesis task, the network is first queried on the set of examples that define the task, and the obtained probabilities determine the frequencies of using instructions in initialization and mutation operators. This priming leads to significant improvements of the odds of successful synthesis on a range of benchmarks.",
• notes = "Also known as \cite{3205629} GECCO-2018 A Recombination of the 27th International Conference on Genetic Algorithms (ICGA-2018) and the 23rd Annual Genetic Programming Conference (GP-2018)",

}

Genetic Programming entries for Pawel Liskowski Iwo Bladek Krzysztof Krawiec

Citations