A game theoretic approach to explain the output of any machine learning model.

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

XAI - An eXplainability toolbox for machine learning

Visualization toolkit for neural networks in PyTorch! Demo -->

Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet

H1st AI solves the critical “cold-start” problem of Industrial AI: encoding human expertise to augment the lack of data, while building a smooth transition toward a machine-learning future. This problem has caused most industrial-AI projects to fail.

📍 Interactive Studio for Explanatory Model Analysis

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

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

[CVPR 2020 Workshop] Official implementation of Score-CAM in Pytorch

Explainability techniques for Graph Networks, applied to a synthetic dataset and an organic chemistry task. Code for the workshop paper "Explainability Techniques for Graph Convolutional Networks" (ICML19)

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

Contextual AI adds explainability to different stages of machine learning pipelines - data, training, and inference - thereby addressing the trust gap between such ML systems and their users. It does not refer to a specific algorithm or ML method — instead, it takes a human-centric view and approach to AI.

TK & TKL - Efficient Transformer-based neural re-ranking models

The implementation of “A Capsule Network for Recommendation and Explaining What You Like and Dislike”, Chenliang Li, Cong Quan, Li Peng, Yunwei Qi, Yuming Deng, Libing Wu, https://dl.acm.org/citation.cfm?doid=3331184.3331216

Modular Python Toolbox for Fairness, Accountability and Transparency Forensics

Amazon SageMaker Solution for explaining credit decisions.

For calculating global feature importance using Shapley values.

Data generator for Arena - interactive XAI dashboard

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

Getting the Anchors Explainer to work in Different Settings

General-purpose library for extracting interpretable models from Multi-Agent Reinforcement Learning systems

The code of AAAI 2020 paper "Transparent Classification with Multilayer Logical Perceptrons and Random Binarization".

Explainability of Deep Learning Models

Concept activation vectors for Keras

Analysis and investigating the confounding effect of accents in E-2-E Automatic Speech Recognition models.

Using / reproducing TRIM from the paper "Transformation Importance with Applications to Cosmology"

ibreakdown is model agnostic predictions explainer with interactions support, library can show contribution of each feature of your prediction value