Learning and Complexity in Genetic Auto-Adaptive Systems
adap-org
2015-06-24 v1 适应与自组织系统
q-bio
摘要
We describe and investigate the learning capablities displayed by a population of self-replicating segments of computer-code subject to random mutation: the tierra environment. We find that learning is achieved through phase transitions that adapt the population to whichever environment it encounters, with a learning rate characterized by the environmental variables. Our results suggest that most effective learning is achieved close to the edge of chaos.
引用
@article{arxiv.adap-org/9401002,
title = {Learning and Complexity in Genetic Auto-Adaptive Systems},
author = {Chris Adami},
journal= {arXiv preprint arXiv:adap-org/9401002},
year = {2015}
}
备注
27 p., tar-compressed uuencoded postscript incl. figures, subm. to "Complex Systems"