TY - UNPB
T1 - Automatically balancing model accuracy and complexity using Solution and Fitness Evolution (SAFE)
AU - Sipper, Moshe
AU - Moore, Jason H.
AU - Urbanowicz, Ryan J.
PY - 2022/6
Y1 - 2022/6
N2 - When seeking a predictive model in biomedical data, one often has more than a single objective in mind, e.g., attaining both high accuracy and low complexity (to promote interpretability). We investigate herein whether multiple objectives can be dynamically tuned by our recently proposed coevolutionary algorithm, SAFE (Solution And Fitness Evolution). We find that SAFE is able to automatically tune accuracy and complexity with no performance loss, as compared with a standard evolutionary algorithm, over complex simulated genetics datasets produced by the GAMETES tool.
AB - When seeking a predictive model in biomedical data, one often has more than a single objective in mind, e.g., attaining both high accuracy and low complexity (to promote interpretability). We investigate herein whether multiple objectives can be dynamically tuned by our recently proposed coevolutionary algorithm, SAFE (Solution And Fitness Evolution). We find that SAFE is able to automatically tune accuracy and complexity with no performance loss, as compared with a standard evolutionary algorithm, over complex simulated genetics datasets produced by the GAMETES tool.
U2 - 10.48550/arXiv.2206.15409
DO - 10.48550/arXiv.2206.15409
M3 - Preprint
BT - Automatically balancing model accuracy and complexity using Solution and Fitness Evolution (SAFE)
ER -