Image classification by evolving bytecode

Created by W.Langdon from gp-bibliography.bib Revision:1.8656

@InProceedings{Pike:2025:evostarLBA,

• author = "Hamish NC Pike",
• title = "Image classification by evolving bytecode",
• booktitle = "Evostar 2025 Late breaking abstracts",
• year = "2025",
• editor = "Antonio M. Mora and Anna I. Esparcia-Alcazar and Maria Sofia Cruz",
• pages = "53--56",
• address = "Trieste",
• month = "23-25 " # apr,
• organisation = "Species",
• keywords = "genetic algorithms, genetic programming, zyme, virtual machine, programming language, evolvable bytecode",
• URL = "https://arxiv.org/abs/2511.17543",
• fulltext_url = "https://zyme.dev/blog/1_image_classification_by_evolving_bytecode",
• size = "4 pages",
• abstract = "We investigate the potential of evolving the bytecode of a biologically-inspired virtual machine as a plausible strategy for machine learning. We simulate evolution with the Zyme language and strand-based virtual machine. Our test problem is classifying handwritten digits from a subset of the MNIST dataset. Beginning with an initial program with performance no better than random guessing, we achieve consistent accuracy improvements through random mutations over 50 generations. Although these results fall short of state-of-the-art methods like neural networks, they demonstrate that adaptive mutations are found consistently and suggest the potential for evolving Zyme bytecode to competitively tackle the full MNIST task. This result also suggests the value of alternative virtual machines architectures in genetic programming, particularly those optimized for evolvability",
• notes = "https://www.evostar.org/2025/late-breaking-abstracts/",

}

Genetic Programming entries for Hamish Nicholl Cathcart Pike

Citations