LIME

Terms from Artificial Intelligence: humans at the heart of algorithms

LIME is a popular local-explanation technique, which seeks to build a linear classifier in the immediate area of a particlar data input..

Used in Chap. 21: pages 338, 341

Links:

doi.org:
article: “Why should I trust you?" : Explaining the predictions of any classifier. M. Ribeiro, S. Singh, and C. Guestrin (2016).

LIME creates local linear classifier at biundary between classes of a black-box model. Image ©2016 Marco Tulio Correia Ribeiro