Explaining black-box models using attribute importance, PDPs, and LIME
Domino Data Lab
AUGUST 1, 2021
Joint training, for example, adds an additional “explanation task” to the original problem and trains the system to solve the two “jointly” (see Bahdanau, 2014). but it generally relies on measuring the entropy in the change of predictions given a perturbation of a feature. See Wei et al. Ribeiro, M.
Let's personalize your content