Social Neural Network Soups with Surprise Minimization

@inproceedings{ zornALIFE23,
    author      = "Maximilian Zorn and Steffen Illium and Thomy Phan and Tanja Katharina Kaiser and Claudia Linnhoff-Popien and Thomas Gabor",
    title       = "Social Neural Network Soups with Surprise Minimization",
    year        = "2023",
    
    
    abstract    = "A recent branch of research in artificial life has constructed artificial chemistry systems whose particles are dynamic neural networks. These particles can be applied to each other and show a tendency towards self-replication of their weight values. We define new interactions for said particles that allow them to recognize one another and learn predictors for each other's behavior. For instance, each particle minimizes its surprise when observing another particle's behavior. Given a special catalyst particle to exert evolutionary selection pressure on the soup of particles, these 'social' interactions are sufficient to produce emergent behavior similar to the stability-pattern previously only achieved via explicit self-replication training.",
    url         = "https://thomyphan.github.io/publication/2023-07-01-alife-zorn",
    eprint      = "https://thomyphan.github.io/files/2023-alife-preprint.pdf",
    location    = "Sapporo, Japan",
    publisher   = "MIT Press Direct",
    booktitle   = "ALIFE 2023: Ghost in the Machine: Proceedings of the 2023 Artificial Life Conference",
    pages       = "65",
    keywords    = "artificial chemistry, neural networks, self-replication, emergent behavior, social systems",
    doi         = "https://doi.org/10.1162/isal_a_00671"
}