From 80aa7e618757a1adb868cd166404f04ab5bf3c80 Mon Sep 17 00:00:00 2001 From: "Anh M. Nguyen" Date: Wed, 11 Nov 2020 14:59:54 -0600 Subject: [PATCH] Added Counterfactual Explanations for Machine Learning --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index 09056e8..b664ec8 100644 --- a/README.md +++ b/README.md @@ -198,6 +198,8 @@ This is an on-going attempt to consolidate interesting efforts in the area of un * Towards robust interpretability with self-explaining neural networks. _Alvarez-Melis and Jaakola 2018_ [pdf](http://people.csail.mit.edu/tommi/papers/SENN_paper.pdf) # C. Counterfactual explanations + +* Counterfactual Explanations for Machine Learning: A Review. _Verma et al. 2020_ [pdf](https://arxiv.org/pdf/2010.10596.pdf) * Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections. _Zhang et al. 2018_ [pdf](http://papers.nips.cc/paper/7736-interpreting-neural-network-judgments-via-minimal-stable-and-symbolic-corrections.pdf) * Counterfactual Visual Explanations. _Goyal et al. 2019_ [pdf](https://arxiv.org/pdf/1904.07451.pdf) * Generative Counterfactual Introspection for Explainable Deep Learning. _Liu et al. 2019_ [pdf](https://arxiv.org/abs/1907.03077)