Cluster-Based Training Selection Outperforms Active Learning for Material Property Prediction
A study of 100 algorithms across 60 prediction tasks reveals that cluster-based training set selection consistently outperforms active learning in ...
A study of 100 algorithms across 60 prediction tasks reveals that cluster-based training set selection consistently outperforms active learning in ...
Researchers developed an auxiliary-lag dependent Gaussian process model utilizing tailored multi-featured kernels and multi-start optimization to deliver improved time series ...
A new multi-genus statistical model improves the accuracy of timber harvest location identification by combining chemical data from multiple tree ...
A closed-loop workflow combining synchrotron GISAXS, automated scattering analysis, and Gaussian process-driven Bayesian optimization found target-satisfying block copolymer processing conditions ...
An online Gaussian-process controller that tightens its own safety limits based on prediction uncertainty retained 4.3 percentage points more battery ...
A seven-year study of Thailand's Bang Pakong estuary shows that tidal distortion strengthens each monsoon season, with shallow-water tidal constituents ...
Researchers used Bayesian optimization with Gaussian process surrogate modeling to design microfluidic deterministic lateral displacement chips that separate circulating tumor ...
Researchers have built a spatio-temporal statistical weather generator that reproduces France's daily temperature patterns, including large-scale persistent heatwaves, from just ...
Researchers at the Italian Institute of Technology used Bayesian optimisation with a Gaussian process surrogate to identify stress-critical poses of ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine