A model explanation system

By Ryan D. Turner. 2016

80 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

A Survey of Methods for Explaining Black Box Models (2018, methodology): “N IMG X X X Grad-CAM [89] Selvaraju et al. 2016 Outcome Expl. SM DNN IMG X X X - [56] Lei et al. 2016 Outcome Expl. SM DNN TXT X X LIME [83] Ribeiro et al. 2016 Outcome Expl. FI AGN ANY X X X X X MES [98] Turner et al. 2016 Outcome Expl. DR AGN ANY X X X NID [71] Olden et al. 2002 Inspection SA NN T”
Interpretable Explanations of Black Boxes by Meaningful Perturbation (2017, methodology): “The idea of explanations as predictors is inspired by the work of [18], which we generalize to new types of explanations, from classification to invariance.”
The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations (2019, methodology): “…used to approximate the decision function of the black-box and build understandable explanations, either using a surrogate model (e.g. a linear model [Ribeiro et al. , 2016] or a decision tree [Hara and Hayashi, 2016]), or by computing meaningful coefﬁcients [Turner, 2015; Lundberg and Lee, 2017]).”
Inverse Classification for Comparison-based Interpretability in Machine Learning (2017, background): “Feature importances (Baehrens et al. 2009; Ribeiro, Singh, and Guestrin 2016), binary rules (Turner 2016) or visualizations (Krause, Perer, and Bertini 2016) for instance give different insights about predictions without any knowledge on the classiﬁer.”
Explainable AI: Interpreting, Explaining and Visualizing Deep Learning (2019, background): “Other approaches seek to identify interpretable representations in order to help understand how an algorithm works [1,11,29].”
Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey (2019, background): “NES [99] any rule extraction local, ante-hoc BETA [73] any decision tree global, ante-hoc PALM [100] any decision tree global, ante-hoc DeepLift [75] any feature importance local, ante-hoc IG [87] any sensitivity analysis global, ante-hoc RETAIN [74] EHR Reverse Time Atten.”
Trustworthy Artificial Intelligence: A Review (2022, methodology): “Other researchers [196] proposed a similar approach that provides explanations based on the formal requirements using the Monte Carlo algorithm.”
Principles and Practice of Explainable Machine Learning (2020, background): “Additional techniques to construct rules explaining a model’s decisions can be found in [82, 83].”
A Model Explanation System: Latest Updates and Extensions (2016, methodology): “Turner (2015) showed how to use standard MES to explain why the SVM classiﬁes Hugo Chavez as George W Bush.”
Fair lending needs explainable models for responsible recommendation (2018, background): “However, recent work on automatic model explanations [43, 50] suggest that it is possible to generate relatively short explanations for the predictions produced for any particular set of inputs and outputs.”
A Survey on the Explainability of Supervised Machine Learning (2020, background): “MES (Turner, 2016) is a general framework which explains the predictions of a binary black box classifier.”