Tag: interpretable machine learning

A new Riemannian framework called HyperSpectrum Geometry lets text classifiers bend the curvature of their semantic space, revealing that emotionally ...

A rough set theory analysis of the METABRIC cohort shows that a compact set of routine clinical variables can moderately ...

Researchers have developed Foldinsight, a framework that uses AlphaFold2-predicted structures and molecular field descriptors to model and spatially interpret the ...

A new ELTE study using interpretable machine learning finds that learning support, accessibility, engagement, usability, and perceived reliability determine whether ...

A new interpretable machine learning study shows that warming in Northeast China's frozen soils decreases with depth, with longwave radiation, ...

Researchers have developed a gradient boosting method that learns sparse oblique rules, producing simpler and more interpretable prediction models with ...

A French research team has developed DiaSeg, a framework that extracts diagonal segments from Dynamic Time Warping paths to create ...

Researchers have introduced PMGL-GAD, a framework that combines training-free green learning features with a global attention disambiguation module to solve ...

Researchers at EPFL have developed MAGNETS, an inherently interpretable neural network that predicts continuous targets from time series by learning ...

A new framework called TDiMS rebuilds molecular descriptors around pairs of chemically meaningful substructures, aiming to make predictions of intramolecular ...