128 Open Source Explainable Ai Software Projects

moDel Agnostic Language for Exploration and eXplanation

Using deep learning to discover interpretable representations for mammogram classification and explanation

Explaining the output of machine learning models with more accurately estimated Shapley values

Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)

code release for Representer point Selection for Explaining Deep Neural Network in NeurIPS 2018

This project provides GOLang implementation of Neuro-Evolution of Augmented Topologies (NEAT) with Novelty Search optimization aimed to solve deceptive tasks with strong local optima

Contrastive Explanation (Foil Trees), developed at TNO/Utrecht University

In-Database Machine Learning

The Machine Learning Toybox for testing the behavior of autonomous agents.

Modular Python Toolbox for Fairness, Accountability and Transparency Forensics

Using / reproducing DAC from the paper "Disentangled Attribution Curves for Interpreting Random Forests and Boosted Trees"

Explains machine learning models fast using the Anchor algorithm originally proposed by marcotcr in 2018

Detect model's attention

Pytorch implementation of "Explainable and Explicit Visual Reasoning over Scene Graphs "

SIREN: A Simulation Framework for Understanding the Effects of Recommender Systems in Online News Environments

Repo for Tang et al, bioRxiv 454793 (2018)

Python library for Ceteris Paribus Plots (What-if plots)

Variable importance via oscillations

A fast Tsetlin Machine implementation employing bit-wise operators, with MNIST demo.

XAI - An eXplainability toolbox for machine learning

Leave One Feature Out Importance

Visualize BERT's self-attention layers on text classification tasks

GAM (Global Attribution Mapping) explains the landscape of neural network predictions across subpopulations

Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" https://arxiv.org/abs/1909.13584

GradCAM Pytorch

🕵️‍♂️ Interpreting Convolutional Neural Network (CNN) Results.

Code, exercises and tutorials of my personal blog ! 📝

Generate Diverse Counterfactual Explanations for any machine learning model.

Fit interpretable models. Explain blackbox machine learning.

Debugging, monitoring and visualization for Python Machine Learning and Data Science

In this work, we propose a deterministic version of Local Interpretable Model Agnostic Explanations (LIME) and the experimental results on three different medical datasets shows the superiority for Deterministic Local Interpretable Model-Agnostic Explanations (DLIME).

All about explainable AI, algorithmic fairness and more

Slides, videos and other potentially useful artifacts from various presentations on responsible machine learning.

(Explainable AI) - Learning Non-Monotonic Logic Programs From Statistical Models Using High-Utility Itemset Mining

Code for NeurIPS 2019 paper ``Self-Critical Reasoning for Robust Visual Question Answering''

Implementation of the Anchors algorithm: Explain black-box ML models

Model Agnostic Counterfactual Explanations

Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible).

📍 Interactive Studio for Explanatory Model Analysis

Interpretability and explainability of data and machine learning models

CEML - Counterfactuals for Explaining Machine Learning models - A Python toolbox

Fast approximate Shapley values in R

In the wild extraction of entities that are found using Flair and displayed using a very elegant front-end.

Examples of Data Science projects and Artificial Intelligence use cases

Visual Explanation using Uncertainty based Class Activation Maps

Information Bottlenecks for Attribution

Article for Special Edition of Information: Machine Learning with Python

[CVPR 2020] "Learning to Structure an Image with Few Colors". Critical structure for network recognition. #explainable-ai

Causal Explanation (CXPlain) is a method for explaining the predictions of any machine-learning model.

Automated Transparent Genetic Feature Engineering

In this part, I've introduced and experimented with ways to interpret and evaluate models in the field of image. (Pytorch)

Interpreting DNNs, Relative attributing propagation

Source code for 'Lemna: Explaining deep learning based security applications'.

💭 Aspect-Based-Sentiment-Analysis: Transformer & Explainable ML (TensorFlow)

A toolkit for efficent computation of saliency maps for explainable AI attribution. This tool was developed at Lawrence Livermore National Laboratory.

The official implementation of "The Shapley Value of Classifiers in Ensemble Games" (CIKM 2021).

A repository for explaining feature attributions and feature interactions in deep neural networks.

A collection of research materials on explainable AI/ML

Explainability of Deep Learning Models

Open source software for machine learning production monitoring : maintain control over production models, detect bias, explain your results.

FairPut - Machine Learning Fairness Framework with LightGBM — Explainability, Robustness, Fairness (by @firmai)

Code to reproduce our paper on probabilistic algorithmic recourse: https://arxiv.org/abs/2006.06831

Amazon SageMaker Solution for explaining credit decisions.

👋 Xplique is a Neural Networks Explainability Toolbox

Code repository for "Interpretable and Accurate Fine-grained Recognition via Region Grouping", CVPR 2020 (Oral)

GEBI: Global Explanations for Bias Identification. Open source code for discovering bias in data with skin lesion dataset

This is a Pytorch implementation of GraphLIME

Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.

Code and data for decision making under strategic behavior

Explainable AI framework for data scientists. Explain & debug any blackbox machine learning model with a single line of code.

Workshop: Explanation and exploration of machine learning models with R and DALEX at eRum 2020

This project provides responsible AI user interfaces for Fairlearn, interpret-community, and Error Analysis, as well as foundational building blocks that they rely on.

This Repo containes the implemnetation of generating Guided-GradCAM for 3D medical Imaging using Nifti file in tensorflow 2.0. Different input files can be used in that case need to edit the input to the Guided-gradCAM model.

💡 Adversarial attacks on model explanations, and evaluation approaches

Human-explainable AI.

This repository contains PyTorch implementation for the baseline models from the paper Utterance-level Dialogue Understanding: An Empirical Study

Code for our USENIX Security 2021 paper -- CADE: Detecting and Explaining Concept Drift Samples for Security Applications

SEG-GRAD-CAM: Interpretable Semantic Segmentation via Gradient-Weighted Class Activation Mapping

A collection of algorithms of counterfactual explanations.

MTUNet: Few-shot Image Classification with Visual Explanations

Dataset and code for "Explainable Automated Fact-Checking for Public Health Claims" from EMNLP 2020.

Repository for the COLING 2020 paper "Explainable Automated Fact-Checking: A Survey."

A Python package for unwrapping ReLU DNNs

ProtoTrees: Neural Prototype Trees for Interpretable Fine-grained Image Recognition, published at CVPR2021

Machine Learning Finite State Machine Models from Data with Genetic Algorithms

CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms

Deep Logic is a python package providing a set of utilities to build deep learning models that are explainable by design.

Explainability for Vision Transformers

Implementation of the paper "Shapley Explanation Networks"

List of relevant resources for machine learning from explanatory supervision

[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.

[CVPR2021] "Visualizing Adapted Knowledge in Domain Transfer". Visualization for domain adaptation. #explainable-ai

Library implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI

PyTorch Explain: Logic Explained Networks in Python.

Explaining dimensionality results using SHAP values

A collection of research papers and software related to explainability in graph machine learning.

Links to conference/journal publications in automated fact-checking (resources for the TACL21 paper).

Essential NLP & ML, short & fast pure Python code