Why Should I Trust You?": Explaining the Predictions of Any Classifier"

Institutions: U of Washington

Authors: M. T. Ribeiro, S. Singh, S. and C. Guestrin

Publication:

Why Should I Trust You?: Explaining the Predictions of Any Classifier, KDD, 2016

Source Code:

https://github.com/marcotcr/lime

Explaining Recurrent Neural Network Predictions in Sentiment Analysis

Institutions: Fraunhofer, TU Berlin, Korea University, Max

Authors: L. Arras, G. Montavon, K-R. Müller and W. Samek

Publication:

Explaining Recurrent Neural Network Predictions in Sentiment Analysis, EMNLP, 2017

Source Code:

https://github.com/ArrasL/LRP_for_LSTM

Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model

Institutions: MIT, U of Washington, Columbia

Authors: B. Letham, C. Rudin, T. McCormick and D. Madigan

Publication:

Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model, Annals of Applied Statistics, 2015

Source Code:

https://github.com/nlarusstone/corels

Principles of Explanatory Debugging to Personalize Interactive Machine Learning

Institutions: Oregon State, City University London

Authors: T. Kulesza, M. Burnett, W-K. Wong and S. Stumpf

Publication:

Principles of Explanatory Debugging to Personalize Interactive Machine Learning, IUI, 2015

Source Code:

https://github.com/fflewddur/IMLPlayground