fig6

Multi-activity derivative automated labeling and margin-sampling active learning for efficient determination of phase boundaries

Figure 6. Uncertainty heat maps of the Au-Ag-Ge system after 25 iterations under different ML algorithms and uncertainty acquisition strategies. Rows correspond to MLP, GPC, and SVC, while columns correspond to MS, LC, and EA. The color scale represents the normalized uncertainty score, with higher values indicating greater predictive uncertainty. ML: Machine learning; MLP: multi-layer perceptron; GPC: Gaussian process classifier; SVC: support vector classifier; MS: margin sampling; LC: least confidence; EA: entropy-based acquisition.

Journal of Materials Informatics
ISSN 2770-372X (Online)
Follow Us

Portico

All published articles are preserved here permanently:

https://www.portico.org/publishers/oae/

Portico

All published articles are preserved here permanently:

https://www.portico.org/publishers/oae/