- author = "Moshe Sipper and Jason H. Moore",
- title = "Conservation machine learning: a case study of random forests",
- journal = "Scientific Reports",
- year = "2021",
- volume = "11",
- pages = "Article number: 3629",
- month = "11 " # feb,
- keywords = "genetic algorithms, genetic programming, Computational science, Computer science, Scientific data, lexicase",
-
URL = "
https://rdcu.be/dYpP3",
-
DOI = "
doi:10.1038/s41598-021-83247-4",
-
code_url = "https://github.com/EpistasisLab",
- size = "6 pages",
- abstract = "Conservation machine learning conserves models across runs, users, and experiments and puts them to good use. We have previously shown the merit of this idea through a small-scale preliminary experiment, involving a single dataset source, 10 datasets, and a single so-called cultivation method—used to produce the final ensemble. focusing on classification tasks, we perform extensive experimentation with conservation random forests, involving 5 cultivation methods (including lexigarden), 6 dataset sources, and 31 datasets. We show that significant improvement can be attained by making use of models we are already in possession of anyway, and envisage the possibility of repositories of models (not merely datasets, solutions, or code), which could be made available to everyone, thus having conservation live up to its name, furthering the cause of data and computational science.",
-
notes = "HIBACHI, GAMETES
Institute for Biomedical Informatics, University of Pennsylvania, Philadelphia, PA, 19104-6021, USA",
