imodels
imodels: a python package for fitting interpretable models - Published in JOSS (2021)
shapr
shapr: An R-package for explaining machine learning models with dependence-aware Shapley values - Published in JOSS (2019)
SIRUS.jl
SIRUS.jl: Interpretable Machine Learning via Rule Extraction - Published in JOSS (2023)
TSInterpret
TSInterpret: A Python Package for the Interpretability of Time Series Classification - Published in JOSS (2023)
mlm-bias
Measuring Biases in Masked Language Models for PyTorch Transformers. Support for multiple social biases and evaluation measures.
grad-cam
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
gam
GAM (Global Attribution Mapping) explains the landscape of neural network predictions across subpopulations
slise
Robust regression algorithm that can be used for explaining black box models (Python implementation)
https://github.com/boyanangelov/sdmexplain
Explainable Species Distribution Modeling
https://github.com/astrazeneca/awesome-shapley-value
Reading list for "The Shapley Value in Machine Learning" (JCAI 2022)
https://github.com/csinva/clinical-rule-development
Building and vetting clinical decision rules.
https://github.com/birkhoffg/explainable-ml-papers
A list of research papers of explainable machine learning.
dashai
DashAI provides a simple graphical user interface (GUI) that guides users through a step-by-step process through creating, training, and saving a model.
explainpolysvm
ExplainPolySVM is a python package to provide interpretation and explainability to Support Vector Machine models trained with polynomial kernels. The package can be used with any SVM model as long as the components of the model can be extracted.
survex
Explainable Machine Learning in Survival Analysis
cctv
This is the code and data to replicate the analysis in Serebrennikov, Skougarevskiy (2023).
slise
Robust regression algorithm that can be used for explaining black box models (R implementation)
pcfi
Per Class Feature Importance (PCFI): an explainability method for decision tree classifiers.
talktomodel
TalkToModel gives anyone with the powers of XAI through natural language conversations 💬!