Machine learning with meta-heuristic feature selection for actinide formation energy and band gap prediction: Quantifying evaluation bias in two-stage materials-property models
Machine learning with meta-heuristic feature selection for actinide formation energy and band gap prediction: Quantifying evaluation bias in two-stage materials-property models. // Data & Knowledge Engineering. – URL: https://www.sciencedirect.com/science/article/pii/S0921452626013517?dgcid=rss_sd_all
Machine learning with meta-heuristic feature selection for actinide formation energy and band gap prediction: Quantifying evaluation bias in two-stage materials-property models. Data & Knowledge Engineering. https://www.sciencedirect.com/science/article/pii/S0921452626013517?dgcid=rss_sd_all
“Machine learning with meta-heuristic feature selection for actinide formation energy and band gap prediction: Quantifying evaluation bias in two-stage materials-property models.” Data & Knowledge Engineering.
@article{article20218,
title = {Machine learning with meta-heuristic feature selection for actinide formation energy and band gap prediction: Quantifying evaluation bias in two-stage materials-property models},
journal = {Data \& Knowledge Engineering},
url = {https://www.sciencedirect.com/science/article/pii/S0921452626013517?dgcid=rss_sd_all}
}
Publication date: 1 February 2027 Source: Physica B: Condensed Matter, Volume 746 Author(s): A. Bouabça, A. Amar, H. Rozale, D. Behera, A. Chahed, F. Boukabrine