From 006aad1a054837f189c05bb2f6b34fe021b58ab5 Mon Sep 17 00:00:00 2001 From: "Lisa B. A. Sousa" <44869855+lisa-sousa@users.noreply.github.com> Date: Thu, 16 May 2024 11:50:52 +0200 Subject: [PATCH] Update shap.rst --- docs/source/_model_agnostic_xai/shap.rst | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/docs/source/_model_agnostic_xai/shap.rst b/docs/source/_model_agnostic_xai/shap.rst index a2b5ae6..b81bcd6 100644 --- a/docs/source/_model_agnostic_xai/shap.rst +++ b/docs/source/_model_agnostic_xai/shap.rst @@ -3,7 +3,7 @@ Introduction to SHapley Additive exPlanations (SHAP) SHapley Additive exPlanationsis a **model-agnostic** method, which means that it is not restricted to a certain model type, and it is a **local** method which means that it only provides explanations for individual samples. -However, the individual explanations can be used to also get **global** interpretations. +However, the individual explanations can be used to also get **global** interpretations. SHAP was introduced in 2017 by `Lundberg et al.`_ For a short video introduction to SHAP, click below: @@ -21,4 +21,5 @@ SHAP provides KernelSHAP, an alternative, kernel-based estimation approach for S References ----------- -Molnar, Christoph. `Interpretable Machine Learning: A Guide for Making Black Box Models Explainable. `_ Lulu.com. 2022. +- Lundberg, S. M., & Lee, S. I. `A unified approach to interpreting model predictions.`_ NeurIPS. 2017 +- Molnar, Christoph. `Interpretable Machine Learning: A Guide for Making Black Box Models Explainable. `_ Lulu.com. 2022.