xai
There are 586 repositories under xai topic.
CADE
Code for our USENIX Security 2021 paper -- CADE: Detecting and Explaining Concept Drift Samples for Security Applications
TorchLRP
A PyTorch 1.6 implementation of Layer-Wise Relevance Propagation (LRP).
fastshap
Fast approximate Shapley values in R
TalkToModel
TalkToModel gives anyone with the powers of XAI through natural language conversations 💬!
ExplainableAI.jl
Explainable AI in Julia.
breakDown
Model Agnostics breakDown plots
DA_visualization
[CVPR2021] "Visualizing Adapted Knowledge in Domain Transfer". Visualization for domain adaptation. #explainable-ai
survex
Explainable Machine Learning in Survival Analysis
rrl
The code of NeurIPS 2021 paper "Scalable Rule-Based Representation Learning for Interpretable Classification" and TPAMI paper "Learning Interpretable Rules for Scalable Data Representation and Classification"
mace
Model Agnostic Counterfactual Explanations
iBreakDown
Break Down with interactions for local explanations (SHAP, BreakDown, iBreakDown)
xaitk-saliency
As part of the Explainable AI Toolkit (XAITK), XAITK-Saliency is an open source, explainable AI framework for visual saliency algorithm interfaces and implementations, built for analytics and autonomy applications.
treeshap
Compute SHAP values for your tree-based models using the TreeSHAP algorithm
survshap
SurvSHAP(t): Time-dependent explanations of machine learning survival models
ml-fairness-framework
FairPut - Machine Learning Fairness Framework with LightGBM — Explainability, Robustness, Fairness (by @firmai)
adaptive-wavelets
Adaptive, interpretable wavelets across domains (NeurIPS 2021)
shapviz
R package for SHAP plots
xai-iml-sota
Interesting resources related to Explainable Artificial Intelligence, Interpretable Machine Learning, Interactive Machine Learning, Human in Loop and Visual Analytics.
shapiq
Shapley Interactions for Machine Learning
expmrc
ExpMRC: Explainability Evaluation for Machine Reading Comprehension
auditor
Model verification, validation, and error analysis
azimuth
Helping AI practitioners better understand their datasets and models in text classification. From ServiceNow.
PIPNet
PIP-Net: Patch-based Intuitive Prototypes Network for Interpretable Image Classification (CVPR 2023)
xplainable
Real-time explainable machine learning for business optimisation
concept-based-xai
Library implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI
effector
Effector - a Python package for global and regional effect methods
TorchPRISM
Principal Image Sections Mapping. Convolutional Neural Network Visualisation and Explanation Framework
eXplain-NNs
Library with XAI methods for NNs
cem
Repository for our NeurIPS 2022 paper "Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off" and our NeurIPS 2023 paper "Learning to Receive Help: Intervention-Aware Concept Embedding Models"
logic_explained_networks
Logic Explained Networks is a python repository implementing explainable-by-design deep learning models.
XAI-Tutorials
Self-explanatory tutorials for different model-agnostic and model-specific XAI methods
iprompt
Finding semantically meaningful and accurate prompts.
fastcam
A toolkit for efficent computation of saliency maps for explainable AI attribution. This tool was developed at Lawrence Livermore National Laboratory.
visual-correspondence-XAI
Official code for NeurIPS 2022 paper https://arxiv.org/abs/2208.00780 Visual correspondence-based explanations improve AI robustness and human-AI team accuracy
LMdiff
A diff tool for language models
yolo-heatmaps
A utility for generating heatmaps of YOLOv8 using Layerwise Relevance Propagation (LRP/CRP).