Risk-aware classification via uncertainty quantification

Murat Sensoy, Lance M. Kaplan, Simon Julier, Maryam Saleki, Federico Cerutti

Abstract: Highlights•Evidential deep learning uses Dirichlet distributions to represent the predictive uncertainty of neural classifiers.•Pignistic probabilities can be used to model rational decision-making under uncertainty.•Risk awareness can be integrated into evidential classifiers using pignistic Dirichlet priors.