Self-replicating artificial neural networks give rise to universal evolutionary dynamics
Fig 1
(A) A juvenile SeRANN individual “learns” to both classify images from the training set and to copy arbitrary genotypes using standard deep-learning techniques. (B) An adult SeRANN then classifies images from the test set and copies its own genotype, producing a classification accuracy, which is its fertility, and replicated genotypes, which are its offspring genotypes. (C) The individual fertility is compared to the population mean fertility to determine the individual’s expected contribution to the offspring generation–which are then sampled from the offspring genotypes of all individuals. (D) Each genotype is decoded to a source code using the RiboDecoder (see Methods) and executed by the Python interpreter. Only valid source codes, which don’t cause execution errors (e.g., due to syntax errors), continue to the next generation. (E) The source code of the ancestor of the population, see Fig B in S1 Text for the genotype and supporting code.