Tag: conformal prediction

A BUPT-1 study selected joint uncertainty geometry for multi-horizon spacecraft power monitoring and reported empirical coverage and sharper power intervals ...

A physics-guided digital-twin framework estimates electric vehicle battery energy minute by minute and is stress-tested across route, operating-regime, vehicle, and ...

A research team proposes a framework of explainable, uncertainty-aware prediction, biologically constrained generative design and iterative design–test–learn cycles to make ...

A new autonomous AI framework called DriftGuard detects, diagnoses, and corrects calibration drift in ocean sensor networks up to three ...

A new neuro-symbolic framework called Delta Semantics keeps machine learning outputs provably consistent with evolving ontologies by attaching checker-validated proof ...

Researchers have developed a conformal calibration method that borrows statistical strength across sparse group-horizon cells to fix hidden coverage gaps ...

Researchers combined positive-unlabeled learning, spatial block cross-validation, bootstrap uncertainty, and conformal calibration to produce a confidence-aware nickel prospectivity map of ...

Researchers show that conformal prediction set sizes and miscoverage changes can distinguish label noise from covariate shift in deployed classifiers ...

Researchers at the University of Sydney have combined path signatures from rough path theory with directed graph spectral modeling to ...

A new study of Bangladesh's 2024 Feni flash flood shows that standard flood-susceptibility machine learning inflates accuracy through spatial leakage ...