Particularity
Neural and Evolutionary Computing
2023-06-13 v1 Artificial Intelligence
Machine Learning
Abstract
We describe a design principle for adaptive systems under which adaptation is driven by particular challenges that the environment poses, as opposed to average or otherwise aggregated measures of performance over many challenges. We trace the development of this "particularity" approach from the use of lexicase selection in genetic programming to "particularist" approaches to other forms of machine learning and to the design of adaptive systems more generally.
Cite
@article{arxiv.2306.06812,
title = {Particularity},
author = {Lee Spector and Li Ding and Ryan Boldi},
journal= {arXiv preprint arXiv:2306.06812},
year = {2023}
}
Comments
Genetic Programming Theory and Practice XX