GPAM: Genetic Programming with Associative Memory

Created by W.Langdon from gp-bibliography.bib Revision:1.7316

@InProceedings{Juza:2023:EuroGP,

• author = "Tadeas Juza and Lukas Sekanina",
• title = "{GPAM}: Genetic Programming with Associative Memory",
• booktitle = "EuroGP 2023: Proceedings of the 26th European Conference on Genetic Programming",
• year = "2023",
• month = "12-14 " # apr,
• editor = "Gisele Pappa and Mario Giacobini and Zdenek Vasicek",
• series = "LNCS",
• volume = "13986",
• publisher = "Springer Verlag",
• address = "Brno, Czech Republic",
• pages = "68--83",
• organisation = "EvoStar, Species",
• keywords = "genetic algorithms, genetic programming, Associative memory, Neural network, ANN, Weight compression, Symbolic regression",
• isbn13 = "978-3-031-29572-0",
• URL = "https://www.fit.vut.cz/research/publication/12860",
• URL = "https://rdcu.be/c8UPG",
• DOI = "doi:10.1007/978-3-031-29573-7_5",
• size = "16 pages",
• abstract = "We focus on the evolutionary design of programs capable of capturing more randomness and outliers in the input data set than the standard genetic programming (GP)-based methods typically allow. We propose Genetic Programming with Associative Memory (GPAM), a GP-based system for symbolic regression which can use a small associative memory to store various data points to better approximate the original data set. The method is evaluated on five standard benchmarks in which a certain number of data points is replaced by randomly generated values. In another case study, GPAM is used as an on-chip generator capable of approximating the weights for a convolutional neural network (CNN) to reduce the access to an external weight memory. Using Cartesian genetic programming (CGP), we evolved expression-memory pairs that can generate weights of a single CNN layer. If the associative memory contains 10percent of the original weights, the weight generator evolved for a convolutional layer can approximate the original weights such that the CNN using the generated weights shows less than a 1percent drop in the classification accuracy on the MNIST data set.",
• notes = "Also known as \cite{FITPUB12860} Part of \cite{Pappa:2023:GP} EuroGP'2023 held in conjunction with EvoCOP2023, EvoMusArt2023 and EvoApplications2023",

}

Genetic Programming entries for Tadeas Juza Lukas Sekanina

Citations