GP-Based Generative Adversarial Models

Created by W.Langdon from gp-bibliography.bib Revision:1.7630

@InProceedings{Machado:2022:GPTP,

• author = "Penousal Machado and Francisco Baeta and Tiago Martins and Joao Correia",
• title = "{GP}-Based Generative Adversarial Models",
• booktitle = "Genetic Programming Theory and Practice XIX",
• year = "2022",
• editor = "Leonardo Trujillo and Stephan M. Winkler and Sara Silva and Wolfgang Banzhaf",
• series = "Genetic and Evolutionary Computation",
• pages = "117--140",
• address = "Ann Arbor, USA",
• month = jun # " 2-4",
• publisher = "Springer",
• keywords = "genetic algorithms, genetic programming, ANN",
• isbn13 = "978-981-19-8459-4",
• DOI = "doi:10.1007/978-981-19-8460-0_6",
• abstract = "We explore the use of Artificial Neural Network (ANN)-guided Genetic Programming (GP) to generate images that the guiding network classifies as belonging to a specific class. The experimental results demonstrate the ability of GP to perform such a task but also the inadequacy of most of the generated images, which can be considered false positives. Based on these findings and following an approach analogous to Generative Adversarial Networks (GANs), we propose an generative adversarial model where GP replaces the traditional GAN’s generator. The experimental results illustrate the advantages of this approach, highlighting the expressive power of GP, its capacity to perform online learning, thus adapting to a dynamic fitness landscape, and its ability to create novel imagery that fits the target classes.",
• notes = "Part of \cite{Banzhaf:2022:GPTP} published after the workshop in 2023",

}

Genetic Programming entries for Penousal Machado Francisco Baeta Tiago Martins Joao Nuno Goncalves Costa Cavaleiro Correia

Citations