Using LIME and SHAP for model interpretability of Machine Learning Black-box models.
-
Updated
Sep 13, 2019 - Jupyter Notebook
Using LIME and SHAP for model interpretability of Machine Learning Black-box models.
Tiny Tutorial on https://arxiv.org/abs/1703.04730
This repository was created as an implementation approach for a project on "Watermarking Deep Neural Networks".
Getting explanations for predictions made by black box models.
A general framework for constructing partial dependence (i.e., marginal effect) plots from various types machine learning models in R.
Black-box Few-shot Knowledge Distillation
Interpreting Categorical Data Classifiers using Explanation-based Locality
Simplicial Homology Global Optimization
📄 [Talk] OFFZONE 2022 / ODS Data Halloween 2022: Black-box attacks on ML models + with use of open-source tools
Generative Adversarial Network (GAN) that can produce tabular samples given datasets, and build a general generative model that receives a black-box as a discriminator and can still generate samples from the tabular data.
A Global Model-Agnostic Rule-Based XAI Method based on Parameterised Event Primitives for Time Series Classifiers
Add a description, image, and links to the black-box-model topic page so that developers can more easily learn about it.
To associate your repository with the black-box-model topic, visit your repo's landing page and select "manage topics."