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). This dataset classifies customers based on a set of attributes into two credit risk groups – good or bad. 1 570 0 570 Name: credit, dtype: int64.
Let's personalize your content