📍 Interactive Studio for Explanatory Model Analysis

A Python library for Secure and Explainable Machine Learning

Explainable Machine Learning in Survival Analysis

[CIKM'2023] "STExplainer: Explainable Spatio-Temporal Graph Neural Networks"

Classification and Object Detection XAI methods (CAM-based, backpropagation-based, perturbation-based, statistic-based) for thyroid cancer ultrasound images

A collection of algorithms of counterfactual explanations.

A utility for generating heatmaps of YOLOv8 using Layerwise Relevance Propagation (LRP/CRP).

Principal Image Sections Mapping. Convolutional Neural Network Visualisation and Explanation Framework

Code repository for the online course Machine Learning Interpretability

Counterfactual SHAP: a framework for counterfactual feature importance

The PyTorch implementation for "DEAL: Disentangle and Localize Concept-level Explanations for VLMs" (ECCV 2024 Strong Double Blind)

t-viSNE: Interactive Assessment and Interpretation of t-SNE Projections

Interpretable Control Exploration and Counterfactual Explanation (ICE) on StyleGAN

Repo of the paper "On the Robustness of Sparse Counterfactual Explanations to Adverse Perturbations"

📊 Language Model Learning a Dataset for Data-Augmented Prediction

Counterfactual Shapley Additive Explanation: Experiments

This repository contains the Business Intelligence insights generated as part of the final project challenge for the DTU Data Science course 42578: Advanced Business Analytics

GEMEX is a novel, model-agnostic Explainable AI (XAI) library grounded in Riemannian information geometry and differential geometry. It treats a trained model as defining a statistical manifold equipped with the Fisher Information Metric and derives all explanations from the intrinsic geometry of that manifold.

An R package providing functions for interpreting and distilling machine learning models

The Pytorch implementation for "Are Data-driven Explanations Robust against Out-of-distribution Data?" (CVPR 2023)