2014, Knowledge Discovery and Metrics

Explaining black-box models using attribute importance, PDPs, and LIME

Domino Data Lab

AUGUST 1, 2021

Because of its architecture, intrinsically explainable ANNs can be optimised not just on its prediction performance, but also on its explainability metric. 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).

Modeling

Modeling Deep Learning Machine Learning Knowledge Discovery

Data Leaders Brief

Explaining black-box models using attribute importance, PDPs, and LIME

Webinars

Stay Connected