TY - JOUR
T1 - Self-replicating artificial neural networks give rise to universal evolutionary dynamics
AU - Shvartzman, Boaz
AU - Ram, Yoav
N1 - Publisher Copyright:
© 2024 Public Library of Science. All rights reserved.
PY - 2024/3
Y1 - 2024/3
N2 - In evolutionary models, mutations are exogenously introduced by the modeler, rather than endogenously introduced by the replicator itself. We present a new deep-learning based computational model, the self-replicating artificial neural network (SeRANN). We train it to (i) copy its own genotype, like a biological organism, which introduces endogenous spontaneous mutations; and (ii) simultaneously perform a classification task that determines its fertility. Evolving 1,000 SeRANNs for 6,000 generations, we observed various evolutionary phenomena such as adaptation, clonal interference, epistasis, and evolution of both the mutation rate and the distribution of fitness effects of new mutations. Our results demonstrate that universal evolutionary phenomena can naturally emerge in a self-replicator model when both selection and mutation are implicit and endogenous. We therefore suggest that SeRANN can be applied to explore and test various evolutionary dynamics and hypotheses.
AB - In evolutionary models, mutations are exogenously introduced by the modeler, rather than endogenously introduced by the replicator itself. We present a new deep-learning based computational model, the self-replicating artificial neural network (SeRANN). We train it to (i) copy its own genotype, like a biological organism, which introduces endogenous spontaneous mutations; and (ii) simultaneously perform a classification task that determines its fertility. Evolving 1,000 SeRANNs for 6,000 generations, we observed various evolutionary phenomena such as adaptation, clonal interference, epistasis, and evolution of both the mutation rate and the distribution of fitness effects of new mutations. Our results demonstrate that universal evolutionary phenomena can naturally emerge in a self-replicator model when both selection and mutation are implicit and endogenous. We therefore suggest that SeRANN can be applied to explore and test various evolutionary dynamics and hypotheses.
UR - http://www.scopus.com/inward/record.url?scp=85189003335&partnerID=8YFLogxK
U2 - 10.1371/journal.pcbi.1012004
DO - 10.1371/journal.pcbi.1012004
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
C2 - 38547320
AN - SCOPUS:85189003335
SN - 1553-734X
VL - 20
JO - PLoS Computational Biology
JF - PLoS Computational Biology
IS - 3
M1 - e1012004
ER -