2009, Knowledge Discovery, Measurement and Optimization

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

Domino Data Lab

AUGUST 1, 2021

but it generally relies on measuring the entropy in the change of predictions given a perturbation of a feature. PDPs for the bicycle count prediction model (Molnar, 2009). Courville, Pascal Vincent, Visualizing Higher-Layer Features of a Deep Network, 2009. Conference on Knowledge Discovery and Data Mining, pp.

Modeling

Modeling Deep Learning Machine Learning Knowledge Discovery

Data Leaders Brief

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

Webinars

Stay Connected